> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to Crowdin

The Crowdin connector lets your AI agent act in each user's Crowdin account. Each user connects their own Crowdin access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 57 tools.

**Authentication:** Bearer Token
**Categories:** Developer Tools, Productivity
**Tools:** 57: 36 read, 16 write, 5 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=CROWDIN)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Crowdin connection

   In **AgentKit > Connections**, create a Crowdin connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'crowdin'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Crowdin:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'crowdin_glossaries_list',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "crowdin"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Crowdin:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="crowdin_glossaries_list",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Crowdin credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'crowdin_approvals_list',
  toolInput: {
    project_id: 123456,
  },
  connector: 'crowdin',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="crowdin_approvals_list",
    tool_input={
        "project_id": 123456,
    },
    connection_name="crowdin",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `crowdin_approvals_list`

List Approvals · Read-only

List translation approvals.
Returns data[] (each with id, user, translationId, languageId, createdAt, stringId) plus pagination.
Use crowdin_approvals_list to see what was proofread.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `exclude_label_ids` (`string`, optional): Label Identifiers. Get via List Labels. Example: abc123
- `file_id` (`integer`, optional): File ID, from crowdin_files_list. Example: 44
- `label_ids` (`string`, optional): Label IDs, comma-separated. Example: 13,27
- `language_id` (`string`, optional): Crowdin language ID, from crowdin_languages_list. Example: de
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, createdAt. Example: createdAt desc. One of: `id`, `createdAt`.
- `string_id` (`integer`, optional): String ID, from crowdin_strings_list. Example: 2814
- `translation_id` (`integer`, optional): Translation Identifier. Get via List String Translations Note: Can't be used with languageId in the same request. Example: 12345

Example input: `{"project_id":123456}`

### `crowdin_branches_list`

List Branches · Read-only

List the version branches of a project.
Returns data[] (each with id, projectId, name, title, createdAt, updatedAt, exportPattern, priority) plus pagination.
Use crowdin_branches_list to find a branchId.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `name` (`string`, optional): Filter by branch name. Example: main
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, title, createdAt, updatedAt, exportPattern, priority. Example: createdAt desc. One of: `id`, `name`, `title`, `createdAt`, `updatedAt`, `exportPattern`, `priority`.

Example input: `{"project_id":123456}`

### `crowdin_build_download_url_get`

Get Build Download Link · Read-only

Get a temporary download link for a finished build ZIP.
Returns data with url, expireIn.
Use crowdin_build_download_url_get once crowdin_build_get reports finished.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `build_id` (`integer`, required): Build ID. Example: 2
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"build_id":2,"project_id":123456}`

### `crowdin_build_get`

Get Build Status · Read-only

Get the status and progress of a translation build.
Returns data with id, projectId, status, progress, createdAt, updatedAt, finishedAt, error, attributes.
Use crowdin_build_get to poll a build.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `build_id` (`integer`, required): Build ID. Example: 2
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"build_id":2,"project_id":123456}`

### `crowdin_builds_list`

List Builds · Read-only

List the translation builds of a project.
Returns data[] (each with id, projectId, status, progress, createdAt, updatedAt, finishedAt, error) plus pagination.
Use crowdin_builds_list to find a recent build.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0

Example input: `{"project_id":123456}`

### `crowdin_comments_list`

List Comments · Read-only

List string comments and issues.
Returns data[] (each with id, text, userId, user, projectId, languageId, type, issueType) plus pagination.
Use crowdin_comments_list to read translator questions.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `file_id` (`integer`, optional): File ID, from crowdin_files_list. Example: 44
- `issue_status` (`string`, optional): Issue status. One of: resolved, unresolved. Example: unresolved. One of: `resolved`, `unresolved`.
- `issue_type` (`string`, optional): Defines issue type. It can be one issue type or a list of comma-separated ones. One of: general_question, translation_mistake, context_request, source_mistake. Example: general_question,translation_mistake. One of: `general_question`, `translation_mistake`, `context_request`, `source_mistake`.
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, text, type, createdAt, resolvedAt, issueStatus, issueType. Example: createdAt desc. One of: `id`, `text`, `type`, `createdAt`, `resolvedAt`, `issueStatus`, `issueType`.
- `string_id` (`integer`, optional): String ID, from crowdin_strings_list. Example: 2814
- `type` (`string`, optional): Comment type. One of: comment, issue. Example: issue. One of: `comment`, `issue`.

Example input: `{"project_id":123456}`

### `crowdin_directories_list`

List Directories · Read-only

List the directories of a project.
Returns data[] (each with id, projectId, branchId, directoryId, name, title, exportPattern, path) plus pagination.
Use crowdin_directories_list to find a directoryId.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `directory_id` (`integer`, optional): Directory ID, from crowdin_directories_list. Example: 4
- `filter` (`string`, optional): Filter by directory name. Example: docs
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, title, createdAt, updatedAt, exportPattern, priority. Example: createdAt desc. One of: `id`, `name`, `title`, `createdAt`, `updatedAt`, `exportPattern`, `priority`.
- `recursion` (`boolean`, optional): Set to 1 to include nested directories. Example: 1

Example input: `{"project_id":123456}`

### `crowdin_file_download_url_get`

Get File Download Link · Read-only

Get a temporary download link for a source file.
Returns data with url, expireIn.
Use crowdin_file_download_url_get to fetch the original source file.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `file_id` (`integer`, required): File ID, from crowdin_files_list. Example: 44
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"file_id":44,"project_id":123456}`

### `crowdin_file_get`

Get File · Read-only

Get one source file with its type, path and status.
Returns data with id, projectId, branchId, directoryId, name, title, context, type, path, status.
Use crowdin_file_get for one file.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `file_id` (`integer`, required): File ID, from crowdin_files_list. Example: 44
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"file_id":44,"project_id":123456}`

### `crowdin_file_progress_get`

Get File Progress · Read-only

Get translation progress of a file per target language.
Returns data[] (each with words, phrases, translationProgress, approvalProgress, qaChecksStatus, languageId, eTag, language) plus pagination.
Use crowdin_file_progress_get for one file.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `file_id` (`integer`, required): File ID, from crowdin_files_list. Example: 44
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0

Example input: `{"file_id":44,"project_id":123456}`

### `crowdin_files_list`

List Files · Read-only

List the source files of a project.
Returns data[] (each with id, projectId, branchId, directoryId, name, title, context, type) plus pagination.
Use crowdin_files_list to find a fileId.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `directory_id` (`integer`, optional): Directory ID, from crowdin_directories_list. Example: 4
- `filter` (`string`, optional): Filter by file name. Example: messages
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, title, status, exportPattern, priority, createdAt, updatedAt. Example: createdAt desc. One of: `id`, `name`, `title`, `status`, `exportPattern`, `priority`, `createdAt`, `updatedAt`.
- `recursion` (`boolean`, optional): Set to 1 to include files in nested directories. Example: 1

Example input: `{"project_id":123456}`

### `crowdin_glossaries_list`

List Glossaries · Read-only

List glossaries.
Returns data[] (each with id, name, userId, terms, languageId, languageIds, defaultProjectIds, projectIds) plus pagination.
Use crowdin_glossaries_list to find a glossary ID.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filter` (`string`, optional): Filter glossaries by name. Example: example
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, userId, createdAt. Example: createdAt desc. One of: `id`, `name`, `userId`, `createdAt`.
- `user_id` (`integer`, optional): List user glossaries. Example: 12345

Example input: `{}`

### `crowdin_glossary_get`

Get Glossary · Read-only

Get one glossary.
Returns data with id, name, userId, terms, languageId, languageIds, defaultProjectIds, projectIds, isShared, webUrl, and more.
Use crowdin_glossary_get for one glossary.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `glossary_id` (`integer`, required): Glossary ID, from crowdin_glossaries_list. Example: 2

Example input: `{"glossary_id":2}`

### `crowdin_glossary_terms_list`

List Glossary Terms · Read-only

List the terms in a glossary.
Returns data[] (each with id, userId, glossaryId, languageId, text, description, partOfSpeech, status) plus pagination.
Use crowdin_glossary_terms_list to check approved terminology.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `glossary_id` (`integer`, required): Glossary ID, from crowdin_glossaries_list. Example: 2
- `concept_id` (`integer`, optional): Filter terms by conceptId __Note:__ Use for terms that have translations. Get via List Concepts. Example: 12345
- `language_id` (`string`, optional): Crowdin language ID, from crowdin_languages_list. Example: de
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, text, description, partOfSpeech, status, type, gender, note, lemma, createdAt, updatedAt. Example: createdAt desc. One of: `id`, `text`, `description`, `partOfSpeech`, `status`, `type`, `gender`, `note`, `lemma`, `createdAt`, `updatedAt`.
- `translation_of_term_id` (`integer`, optional): Filter terms by termId __Note:__ Use for terms that have translations. Example: 12345
- `user_id` (`integer`, optional): Project Member Identifier. Get via List Project Members. Example: 12345

Example input: `{"glossary_id":2}`

### `crowdin_labels_list`

List Labels · Read-only

List the string labels in a project.
Returns data[] (each with id, title) plus pagination.
Use crowdin_labels_list to find labelIds.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, title. Example: createdAt desc. One of: `id`, `title`.

Example input: `{"project_id":123456}`

### `crowdin_language_progress_get`

Get Language Progress · Read-only

Get translation progress of each file for one target language.
Returns data[] (each with words, phrases, translationProgress, approvalProgress, qaChecksStatus, fileId, eTag) plus pagination.
Use crowdin_language_progress_get to see what is left in one language.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `language_id` (`string`, required): Crowdin language ID, from crowdin_languages_list. Example: de
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_ids` (`string`, optional): Filter results to files of the specified branches, including files in their nested directories. It can be one ID or a list of comma-separated ID values. Up to 50 values. Get via List Branches __Note:__ Can't be used with directoryIds or fileIds in the same request. Example: 1,2,3
- `directory_ids` (`string`, optional): Filter results to files of the specified directories, including files in their nested directories. It can be one ID or a list of comma-separated ID values. Up to 50 values. Get via List Directories __Note:__ Can't be used with branchIds or fileIds in the same request. Example: 1,2,3
- `file_ids` (`string`, optional): Filter results to the specified files. It can be one ID or a list of comma-separated ID values. Up to 50 values. Get via List Files __Note:__ Can't be used with branchIds or directoryIds in the same request. Example: 1,2,3
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0

Example input: `{"language_id":"<language_id>","project_id":123456}`

### `crowdin_language_translations_list`

List Language Translations · Read-only

List translations in one language, optionally for given strings or a file.
Returns data[] (each with provider, providerId, isPreTranslated, matchRate, matchType, stringId, translationId, user) plus pagination.
Use crowdin_language_translations_list to export or review a language.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `language_id` (`string`, required): Crowdin language ID, from crowdin_languages_list. Example: de
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `approved_only` (`integer`, optional): Only approved translations. One of: 0, 1. Example: 0. One of: `0`, `1`.
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `directory_id` (`integer`, optional): Directory ID, from crowdin_directories_list. Example: 4
- `file_id` (`integer`, optional): File ID, from crowdin_files_list. Example: 44
- `label_ids` (`string`, optional): Label IDs, comma-separated. Example: 13,27
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: text, stringId, translationId, createdAt. Example: createdAt desc. One of: `text`, `stringId`, `translationId`, `createdAt`.
- `string_ids` (`string`, optional): String IDs, comma-separated. Example: 2814,2815

Example input: `{"language_id":"<language_id>","project_id":123456}`

### `crowdin_languages_list`

List Languages · Read-only

List the languages Crowdin supports, with their IDs and locale codes.
Returns data[] (each with id, name, editorCode, twoLettersCode, threeLettersCode, locale, androidCode, bcp47Code) plus pagination.
Use crowdin_languages_list to find a languageId.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0

Example input: `{}`

### `crowdin_members_list`

List Project Members · Read-only

List the members of a project with their roles.
Returns data[] (each with id, username, fullName, role, permissions, roles, avatarUrl, joinedAt) plus pagination.
Use crowdin_members_list to find assignees for tasks.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `language_id` (`string`, optional): Filter by language. Example: de
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, username, fullName. Example: createdAt desc. One of: `id`, `username`, `fullName`.
- `role` (`string`, optional): Filter by role. One of: all, manager, developer, language_coordinator, proofreader, translator, blocked, pending. Example: translator. One of: `all`, `manager`, `developer`, `language_coordinator`, `proofreader`, `translator`, `blocked`, `pending`.
- `search` (`string`, optional): Filter by username, first or last name. Example: anna

Example input: `{"project_id":123456}`

### `crowdin_mts_list`

List MT Engines · Read-only

List the machine translation engines set up on the account.
Returns data[] (each with id, name, type, credentials, supportedLanguageIds, supportedLanguagePairs) plus pagination.
Use crowdin_mts_list to find an engine ID.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0

Example input: `{}`

### `crowdin_pre_translation_get`

Get Auto-Translation Status · Read-only

Get the status and progress of an auto-translation.
Returns data with identifier, status, progress, attributes, createdAt, updatedAt, startedAt, finishedAt.
Use crowdin_pre_translation_get after crowdin_pre_translation_apply.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `job_identifier` (`string`, required): Auto-translation ID returned by crowdin_pre_translation_apply. Example: 9e7de270-4f83-41cb-b606-2f90631f26e2
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"job_identifier":"<job_identifier>","project_id":123456}`

### `crowdin_project_get`

Get Project · Read-only

Get one project with its source and target languages and settings.
Returns data with id, type, userId, sourceLanguageId, targetLanguageIds, languageAccessPolicy, name, cname, identifier, description, and more.
Use crowdin_project_get for one project.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"project_id":123456}`

### `crowdin_project_progress_get`

Get Project Progress · Read-only

Get translation and approval progress per target language.
Returns data[] (each with words, phrases, translationProgress, approvalProgress, qaChecksStatus, languageId, language) plus pagination.
Use crowdin_project_progress_get for an overview. Use crowdin_file_progress_get for one file.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `language_ids` (`string`, optional): Filter progress by Language Identifier. Get via Project Target Languages. Example: abc123
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0

Example input: `{"project_id":123456}`

### `crowdin_projects_list`

List Projects · Read-only

List the projects you can access.
Returns data[] (each with id, type, userId, sourceLanguageId, targetLanguageIds, languageAccessPolicy, name, cname) plus pagination.
Use crowdin_projects_list to find a project ID. Use crowdin_project_get for one project.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filter` (`string`, optional): Filter projects by name. Example: example
- `has_manager_access` (`integer`, optional): Set to 1 to list only projects you manage. One of: 1, 0. Example: 1. One of: `1`, `0`.
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, identifier, description, createdAt, updatedAt, lastActivity. Example: createdAt desc. One of: `id`, `name`, `identifier`, `description`, `createdAt`, `updatedAt`, `lastActivity`.
- `type` (`integer`, optional): Project type: 0 file-based, 1 string-based. One of: 0, 1. Example: 0. One of: `0`, `1`.
- `user_id` (`integer`, optional): Only projects of this user. Example: 12

Example input: `{}`

### `crowdin_report_download_url_get`

Get Report Download Link · Read-only

Get a temporary download link for a finished report.
Returns data with url, expireIn.
Use crowdin_report_download_url_get once crowdin_report_get reports finished.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `report_id` (`string`, required): Report ID. Example: 50fb3506-4127-4ba8-8296-f97dc7e3e0c3

Example input: `{"project_id":123456,"report_id":"<report_id>"}`

### `crowdin_report_get`

Get Report Status · Read-only

Get the status of a report being generated.
Returns data with identifier, status, progress, attributes, createdAt, updatedAt, startedAt, finishedAt.
Use crowdin_report_get after crowdin_report_generate.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `report_id` (`string`, required): Report ID returned by crowdin_report_generate. Example: 50fb3506-4127-4ba8-8296-f97dc7e3e0c3

Example input: `{"project_id":123456,"report_id":"<report_id>"}`

### `crowdin_screenshots_list`

List Screenshots · Read-only

List the context screenshots in a project.
Returns data[] (each with id, userId, url, webUrl, name, size, tagsCount, tags) plus pagination.
Use crowdin_screenshots_list to see what visual context translators have.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `exclude_label_ids` (`string`, optional): Label Identifiers. Get via List Labels. Example: abc123
- `label_ids` (`string`, optional): Label IDs, comma-separated. Example: 13,27
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, tagsCount, createdAt, updatedAt. Example: createdAt desc. One of: `id`, `name`, `tagsCount`, `createdAt`, `updatedAt`.
- `search` (`string`, optional): Search screenshots by name, tagged strings or file names that include screenshots. Example: acme
- `string_id` (`integer`, optional): String ID, from crowdin_strings_list. Example: 2814
- `string_ids` (`string`, optional): String Identifiers. Get via List Strings. __Note:__ Can't be used with stringId in the same request. Example: 1,2,3,4,5

Example input: `{"project_id":123456}`

### `crowdin_string_get`

Get String · Read-only

Get one source string with its context and labels.
Returns data with id, projectId, branchId, identifier, text, type, context, maxLength, isHidden, isDuplicate, and more.
Use crowdin_string_get for one string.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `string_id` (`integer`, required): String ID, from crowdin_strings_list. Example: 2814

Example input: `{"project_id":123456,"string_id":2814}`

### `crowdin_string_translations_list`

List String Translations · Read-only

List the translations of one string in one language.
Returns data[] of translations (id, text, user, rating, createdAt) plus pagination.
Use crowdin_string_translations_list for one string. Use crowdin_language_translations_list for a whole language.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `language_id` (`string`, required): Crowdin language ID, from crowdin_languages_list. Example: de
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `file_id` (`integer`, optional): File ID, from crowdin_files_list. Example: 44
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, text, rating, createdAt. Example: createdAt desc. One of: `id`, `text`, `rating`, `createdAt`.
- `string_id` (`integer`, optional): String ID, from crowdin_strings_list. Example: 2814

Example input: `{"language_id":"<language_id>","project_id":123456}`

### `crowdin_strings_list`

List Strings · Read-only

List source strings, filtered by file, branch, directory, task, label or text.
Returns data[] (each with id, projectId, branchId, identifier, text, type, context, maxLength) plus pagination.
Use crowdin_strings_list to find a stringId.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `directory_id` (`integer`, optional): Directory ID, from crowdin_directories_list. Example: 4
- `file_id` (`integer`, optional): File ID, from crowdin_files_list. Example: 44
- `filter` (`string`, optional): Text to search for in the string text, identifier or context (see scope). Example: Welcome
- `label_ids` (`string`, optional): Label IDs, comma-separated. Example: 13,27
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, text, identifier, context, createdAt, updatedAt, type. Example: createdAt desc. One of: `id`, `text`, `identifier`, `context`, `createdAt`, `updatedAt`, `type`.
- `scope` (`string`, optional): Where filter searches: text, identifier or context. One of: identifier, text, context. Example: text. One of: `identifier`, `text`, `context`.
- `task_id` (`integer`, optional): Task ID, from crowdin_tasks_list. Example: 2

Example input: `{"project_id":123456}`

### `crowdin_task_get`

Get Task · Read-only

Get one task with its files, assignees, deadline and progress.
Returns data with id, projectId, creatorId, type, status, title, batchId, assignees, assignedTeams, progress, and more.
Use crowdin_task_get for one task.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `task_id` (`integer`, required): Task ID, from crowdin_tasks_list. Example: 2

Example input: `{"project_id":123456,"task_id":2}`

### `crowdin_tasks_list`

List Tasks · Read-only

List translation and proofreading tasks in a project.
Returns data[] (each with id, projectId, creatorId, type, status, title, batchId, assignees) plus pagination.
Use crowdin_tasks_list to track work. Use crowdin_task_get for one task.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `assignee_id` (`integer`, optional): Filter by assignee user ID. Example: 12
- `batch_id` (`integer`, optional): Filter by task batch. Get batchId via List Tasks. Example: 12345
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, type, title, status, description, createdAt, updatedAt, deadline, startedAt, resolvedAt. Example: createdAt desc. One of: `id`, `type`, `title`, `status`, `description`, `createdAt`, `updatedAt`, `deadline`, `startedAt`, `resolvedAt`.
- `status` (`string`, optional): Filter by status. One of: todo, in_progress, done, closed. Example: in_progress. One of: `todo`, `in_progress`, `done`, `closed`.

Example input: `{"project_id":123456}`

### `crowdin_tm_segments_list`

List TM Segments · Read-only

List the segments (source and translation pairs) of a translation memory.
Returns data[] (each with id, records) plus pagination.
Use crowdin_tm_segments_list to inspect a TM.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `tm_id` (`integer`, required): Translation memory ID, from crowdin_tms_list. Example: 4
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id. Example: createdAt desc. One of: `id`.

Example input: `{"tm_id":4}`

### `crowdin_tms_list`

List Translation Memories · Read-only

List translation memories.
Returns data[] (each with id, userId, name, languageId, languageIds, segmentsCount, defaultProjectIds, projectIds) plus pagination.
Use crowdin_tms_list to find a TM ID.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filter` (`string`, optional): Filter TMs by name. Example: example
- `limit` (`integer`, optional): Maximum number of items to return (1 to 500, default 25). Example: 100
- `offset` (`integer`, optional): Number of items to skip. Example: 0
- `order_by` (`string`, optional): Sort, as field and direction pairs. One of: id, name, userId, createdAt. Example: createdAt desc. One of: `id`, `name`, `userId`, `createdAt`.
- `user_id` (`integer`, optional): Project Member Identifier. Get via List Project Members. Example: 12345

Example input: `{}`

### `crowdin_translation_get`

Get Translation · Read-only

Get one translation.
Returns data with the translation: id, text, stringId, languageId, user, rating and createdAt.
Use crowdin_translation_get for one translation.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `translation_id` (`integer`, required): Translation ID. Example: 190695

Example input: `{"project_id":123456,"translation_id":190695}`

### `crowdin_user_get`

Get Authenticated User · Read-only

Get the Crowdin user the token belongs to.
Returns data with id, username, email, emailVerified, fullName, avatarUrl, createdAt, lastSeen, twoFactor, timezone.
Use crowdin_user_get to check the connection.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `crowdin_approval_create`

Approve Translation · Write

Approve a translation.
Returns data with id, user, translationId, languageId, createdAt, stringId.
Use crowdin_approval_create to mark a translation as proofread.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `translation_id` (`integer`, required): Translation ID to approve. Example: 190695

Example input: `{"project_id":123456,"translation_id":190695}`

### `crowdin_build_create`

Build Project Translations · Write

Start a build of the project translations (a ZIP of translated files). Runs asynchronously.
Returns data with id, projectId, status, progress, createdAt, updatedAt, finishedAt, error, attributes.
Use crowdin_build_create, poll crowdin_build_get, then crowdin_build_download_url_get.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `export_approved_only` (`boolean`, optional): Defines whether to export only approved strings More info. Example: False
- `skip_untranslated_files` (`boolean`, optional): Defines whether to export only translated files __Note:__ true value can't be used with skipUntranslatedStrings=true in same request More info. Example: False
- `skip_untranslated_strings` (`boolean`, optional): Defines whether to export only translated strings __Note:__ true value can't be used with skipUntranslatedFiles=true in same request More info. Example: False
- `target_language_ids` (`array`, optional): Languages to include (default all). Example: ["de"]

Example input: `{"project_id":123456}`

### `crowdin_comment_create`

Add Comment · Write

Add a comment or issue to a string.
Returns data with id, text, userId, user, projectId, languageId, type, issueType, issueStatus, resolverId, and more.
Use crowdin_comment_create to answer a translator or report a source problem.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `string_id` (`integer`, required): String ID, from crowdin_strings_list. Example: 2814
- `text` (`string`, required): Comment text. Example: "Save" here means saving a file.
- `type` (`string`, required): comment or issue. One of: comment, issue. Example: comment. One of: `comment`, `issue`.
- `attachments` (`array`, optional): List of attachments to be added to the comment. Each object must contain id (Storage Identifier). Get via List Storages. Example: [{"key": "value"}]
- `issue_type` (`string`, optional): Defines issue type. One of: general_question, translation_mistake, context_request, source_mistake. Example: translation_mistake. One of: `general_question`, `translation_mistake`, `context_request`, `source_mistake`.
- `target_language_id` (`string`, optional): Language the comment is about. Example: de

Example input: `{"project_id":123456,"string_id":2814,"text":"Save","type":"comment"}`

### `crowdin_directory_create`

Create Directory · Write

Create a directory in a project.
Returns data with id, projectId, branchId, directoryId, name, title, exportPattern, path, priority, createdAt, and more.
Use crowdin_directory_create to organise source files.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Directory name. Example: docs
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `branch_id` (`integer`, optional): Branch ID, from crowdin_branches_list. Example: 34
- `directory_id` (`integer`, optional): Directory ID, from crowdin_directories_list. Example: 4
- `export_pattern` (`string`, optional): Export path pattern for translations. Example: /%locale%/%original_file_name%
- `priority` (`string`, optional): Defines priority level for each branch. One of: low, normal, high. Example: normal. One of: `low`, `normal`, `high`.
- `title` (`string`, optional): Display title. Example: Documentation

Example input: `{"name":"<name>","project_id":123456}`

### `crowdin_glossary_term_create`

Add Glossary Term · Write

Add a term to a glossary.
Returns data with id, userId, glossaryId, languageId, text, description, partOfSpeech, status, type, gender, and more.
Use crowdin_glossary_term_create to define terminology.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `glossary_id` (`integer`, required): Glossary ID, from crowdin_glossaries_list. Example: 2
- `language_id` (`string`, required): Language of the term. Example: en
- `text` (`string`, required): Term. Example: dashboard
- `concept_id` (`integer`, optional): Defines whether to add translation to the existing term. Get concept_id via List Terms or via List Concepts. Example: 12345
- `description` (`string`, optional): Definition. Example: The main overview screen
- `gender` (`string`, optional): Gender. One of: masculine, feminine, neuter, other. Example: masculine. One of: `masculine`, `feminine`, `neuter`, `other`.
- `note` (`string`, optional): Any kind of note, such as a usage note, explanation, or instruction. Example: Called to confirm the renewal.
- `part_of_speech` (`string`, optional): Term part of speech. One of: adjective, adposition, adverb, auxiliary, coordinating conjunction, determiner, interjection, noun, numeral, particle, pronoun, proper noun, subordinating conjunction, verb, other. Example: verb. One of: `adjective`, `adposition`, `adverb`, `auxiliary`, `coordinating conjunction`, `determiner`, `interjection`, `noun`, `numeral`, `particle`, `pronoun`, `proper noun`, `subordinating conjunction`, `verb`, `other`.
- `status` (`string`, optional): Term status. One of: preferred, admitted, not recommended, obsolete, draft. Example: preferred. One of: `preferred`, `admitted`, `not recommended`, `obsolete`, `draft`.
- `type` (`string`, optional): Term type. One of: full form, acronym, abbreviation, short form, phrase, variant. Example: abbreviation. One of: `full form`, `acronym`, `abbreviation`, `short form`, `phrase`, `variant`.
- `url` (`string`, optional): Base URL. Example: https://example.com

Example input: `{"glossary_id":2,"language_id":"<language_id>","text":"Save"}`

### `crowdin_label_create`

Create Label · Write

Create a string label.
Returns data with id, title.
Use crowdin_label_create to tag strings for tasks or filters.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `title` (`string`, required): Label title. Example: release-2.0

Example input: `{"project_id":123456,"title":"<title>"}`

### `crowdin_mt_translate`

Translate with MT · Write

Translate one or more strings with a machine translation engine.
Returns data with sourceLanguageId, targetLanguageId, strings, translations.
Use crowdin_mt_translate for an instant machine translation.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `mt_id` (`integer`, required): MT engine ID from crowdin_mts_list. Example: 2
- `strings` (`array`, required): Texts to translate. Example: ["Welcome back!"]
- `target_language_id` (`string`, required): Target language ID. Example: de
- `language_recognition_provider` (`string`, optional): Select a provider for language recognition __Note:__ Is required if the source language is not selected. One of: crowdin, engine. Example: crowdin. One of: `crowdin`, `engine`.
- `source_language_id` (`string`, optional): Source language ID. Example: en

Example input: `{"mt_id":2,"strings":["Welcome back!"],"target_language_id":"<target_language_id>"}`

### `crowdin_pre_translation_apply`

Apply Auto-Translation · Write

Pre-translate files with translation memory, machine translation or AI for target languages. Runs asynchronously.
Returns data with identifier, status, progress, attributes, createdAt, updatedAt, startedAt, finishedAt.
Use crowdin_pre_translation_apply to fill translations automatically, then poll crowdin_pre_translation_get.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `language_ids` (`array`, required): Target language IDs. Example: ["de", "fr"]
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `auto_approve_option` (`string`, optional): Defines which translations added by TM auto-translation should be auto-approved. Available values: - 'all' – all - 'perfectMatchOnly' – with perfect TM match - 'exceptAutoSubstituted' – all (skip auto-substituted suggestions) - 'perfectMatchApprovedOnly' - with perfect TM match (approved previously) - 'none' – no auto-approve. One of: all, exceptAutoSubstituted, perfectMatchApprovedOnly, perfectMatchOnly, none. Example: all. One of: `all`, `exceptAutoSubstituted`, `perfectMatchApprovedOnly`, `perfectMatchOnly`, `none`.
- `branch_ids` (`array`, optional): Branches array that should be translated. Includes all nested files. Example: [1, 2]
- `duplicate_translations` (`boolean`, optional): Adds translations even if the same translation already exists. Default is false. __Note:__ Cannot be used when replaceTranslationsOption is all (replacing all translations already overrides duplicate handling). Example: false
- `engine_id` (`integer`, optional): Machine translation engine ID (for method mt), from crowdin_mts_list. Example: 2
- `file_ids` (`array`, optional): File IDs to pre-translate. Example: [44, 46]
- `label_ids` (`array`, optional): Label IDs, comma-separated. Example: 13,27
- `method` (`string`, optional): Method: tm, mt or ai. One of: tm, mt, ai. Example: tm. One of: `tm`, `mt`, `ai`.

Example input: `{"language_ids":["de","fr"],"project_id":123456}`

### `crowdin_project_create`

Create Project · Write

Create a file-based project with a source language and target languages.
Returns data with id, type, userId, sourceLanguageId, targetLanguageIds, languageAccessPolicy, name, cname, identifier, description, and more.
Use crowdin_project_create for a new localization project.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Project name. Example: Website
- `source_language_id` (`string`, required): Source language ID. Example: en
- `description` (`string`, optional): Project description. Example: Marketing site strings
- `identifier` (`string`, optional): Project URL identifier. Example: acme-website
- `is_mt_allowed` (`boolean`, optional): Allows machine translations (Microsoft Translator, Google Translate) be visible for translators in the Editor. Example: False
- `language_access_policy` (`string`, optional): Defines access to project languages. Available values: * open – each project user can access all project languages * moderate – users should join each project language separately. One of: open, moderate. Example: moderate. One of: `open`, `moderate`.
- `target_language_ids` (`array`, optional): Target language IDs. Example: ["de", "fr", "es-ES"]
- `use_global_tm` (`boolean`, optional): If true - machine translations from connected MT engines (e.g. Microsoft Translator, Google Translate) will appear as suggestions in the Editor. __Note:__ If your organization plan is free or opensource - default value of this one will be true. Example: False
- `visibility` (`string`, optional): Defines how users can join the project. Available values: * open – anyone can join the project * private – only invited users can join the project. One of: open, private. Example: private. One of: `open`, `private`.

Example input: `{"name":"<name>","source_language_id":"<source_language_id>"}`

### `crowdin_project_update`

Update Project · Write

Change project settings with JSON Patch operations.
Returns data with id, type, userId, sourceLanguageId, targetLanguageIds, languageAccessPolicy, name, cname, identifier, description, and more.
Use crowdin_project_update to rename a project or change its target languages.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `operations` (`array`, required): JSON Patch operations on project settings. Example: [{"op": "replace", "path": "/targetLanguageIds", "value": ["de", "fr"]}]
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"operations":[{"op":"replace","path":"/context","value":"Button label"}],"project_id":123456}`

### `crowdin_report_generate`

Generate Report · Write

Start generating a project report (for example costs estimation or top members). Runs asynchronously.
Returns data with identifier, status, progress, attributes, createdAt, updatedAt, startedAt, finishedAt.
Use crowdin_report_generate, then poll crowdin_report_get.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Report type. One of: pre-translate-efficiency, pre-translate-accuracy. Example: top-members. One of: `pre-translate-efficiency`, `pre-translate-accuracy`.
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `schema` (`object`, required): Report options for the chosen type. Example: {"unit": "words", "format": "json", "dateFrom": "2026-10-01T00:00:00+00:00", "dateTo": "2026-10-31T23:59:59+00:00"}

Example input: `{"name":"pre-translate-efficiency","project_id":123456,"schema":{"unit":"words","format":"json","dateFrom":"2026-10-01T00:00:00+00:00","dateTo":"2026-10-31T23:59:59+00:00"}}`

### `crowdin_string_create`

Create String · Write

Add a source string to a file.
Returns data with id, projectId, branchId, identifier, text, type, context, maxLength, isHidden, isDuplicate, and more.
Use crowdin_string_create to add a new key.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `file_id` (`integer`, required): File ID, from crowdin_files_list. Example: 44
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `text` (`string`, required): Source text. Example: Welcome back!
- `context` (`string`, optional): Context for translators. Example: Heading on the home page
- `identifier` (`string`, optional): String key. Example: home.welcome
- `is_hidden` (`boolean`, optional): Defines whether to make string unavailable for translation. Example: False
- `label_ids` (`array`, optional): Label IDs, comma-separated. Example: 13,27
- `max_length` (`integer`, optional): Maximum translation length. Example: 40

Example input: `{"file_id":44,"project_id":123456,"text":"Save"}`

### `crowdin_string_update`

Update String · Write

Edit a source string with JSON Patch operations.
Returns data with id, projectId, branchId, identifier, text, type, context, maxLength, isHidden, isDuplicate, and more.
Use crowdin_string_update to change a string text or context.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `operations` (`array`, required): JSON Patch operations on the string. Example: [{"op": "replace", "path": "/context", "value": "Button label"}]
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `string_id` (`integer`, required): String ID, from crowdin_strings_list. Example: 2814
- `update_option` (`string`, optional): Defines whether to keep existing translations and approvals for updated string. __NOTE:__ Applied only when text or identifier is changed. One of: keep_translations_and_approvals, keep_translations, clear_translations_and_approvals. Example: keep_translations_and_approvals. One of: `keep_translations_and_approvals`, `keep_translations`, `clear_translations_and_approvals`.

Example input: `{"operations":[{"op":"replace","path":"/context","value":"Button label"}],"project_id":123456,"string_id":2814}`

### `crowdin_task_create`

Create Task · Write

Create a translation or proofreading task for files in a language.
Returns data with id, projectId, creatorId, type, status, title, batchId, assignees, assignedTeams, progress, and more.
Use crowdin_task_create to assign work.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `language_id` (`string`, required): Crowdin language ID, from crowdin_languages_list. Example: de
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `title` (`string`, required): Task title. Example: Translate release 2.0 into German
- `type` (`integer`, required): Task type: 0 translate, 1 proofread. One of: 0, 1. Example: 0. One of: `0`, `1`.
- `assignees` (`array`, optional): Assignees, each with an id and optional wordsCount. Example: [{"id": 12}]
- `branch_ids` (`array`, optional): Branch Identifiers. Get via List Branches __Note:__ One of fields fileIds, directoryIds or branchIds is required. They cannot be provided simultaneously. Example: [1, 2]
- `deadline` (`string`, optional): Deadline, ISO 8601. Example: 2026-12-01T17:00:00+00:00
- `description` (`string`, optional): Task description. Example: Short description
- `file_ids` (`array`, optional): File IDs. Example: [44]
- `label_ids` (`array`, optional): Label IDs, comma-separated. Example: 13,27
- `skip_assigned_strings` (`boolean`, optional): Skip strings already included in other tasks. Example: True
- `status` (`string`, optional): Task status. One of: todo, in_progress. Example: todo. One of: `todo`, `in_progress`.

Example input: `{"language_id":"<language_id>","project_id":123456,"title":"<title>","type":0}`

### `crowdin_task_update`

Update Task · Write

Edit a task with JSON Patch operations, for example its status or deadline.
Returns data with id, projectId, creatorId, type, status, title, batchId, assignees, assignedTeams, progress, and more.
Use crowdin_task_update to close or reschedule a task.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `operations` (`array`, required): JSON Patch operations on the task. Example: [{"op": "replace", "path": "/status", "value": "done"}]
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `task_id` (`integer`, required): Task ID, from crowdin_tasks_list. Example: 2

Example input: `{"operations":[{"op":"replace","path":"/status","value":"done"}],"project_id":123456,"task_id":2}`

### `crowdin_translation_create`

Add Translation · Write

Add a translation for a string in a target language.
Returns data with the translation: id, text, stringId, languageId, user, rating and createdAt.
Use crowdin_translation_create to translate a string.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `language_id` (`string`, required): Target language ID. Example: de
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `string_id` (`integer`, required): String ID, from crowdin_strings_list. Example: 2814
- `text` (`string`, required): Translated text. Example: Willkommen zurück!
- `add_to_tm` (`boolean`, optional): Defines whether to add translation to TM. Example: False
- `is_pre_translated` (`boolean`, optional): Defines whether this is an auto-translated translation. Example: True
- `plural_category_name` (`string`, optional): Plural form. Acceptable keys are zero, one, two, few, many, and other __Note:__ Will be saved only if the source string has plurals and pluralCategoryName is equal to the one available for the language you add translations to. Example: few
- `provider` (`string`, optional): Translation provider type. Required when providerId or isPreTranslated is specified __Note__: global_tm value can't be used with providerId in same request. One of: tm, global_tm, google, microsoft, crowdin, deepl, amazon, google_automl, modernmt, custom_mt, ai. Example: tm. One of: `tm`, `global_tm`, `google`, `microsoft`, `crowdin`, `deepl`, `amazon`, `google_automl`, `modernmt`, `custom_mt`, `ai`.
- `provider_id` (`integer`, optional): Provider specific identifier. Get via: * If provider is tm - List TMs * If provider is ai - List AI Prompts * If provider is google, microsoft, crowdin, deepl, amazon, google_automl, modernmt or custom_mt - List MTs __Note__: Can't be used if provider value is global_tm. Example: 123

Example input: `{"language_id":"<language_id>","project_id":123456,"string_id":2814,"text":"Save"}`

### `crowdin_file_delete`

Delete File · Destructive

Delete a source file and its translations.
Returns an empty response on success.
Use crowdin_file_delete to remove a file from a project.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `file_id` (`integer`, required): File ID, from crowdin_files_list. Example: 44
- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"file_id":44,"project_id":123456}`

### `crowdin_project_delete`

Delete Project · Destructive

Delete a project with all its files and translations.
Returns an empty response on success.
Use crowdin_project_delete only to remove a project for good.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456

Example input: `{"project_id":123456}`

### `crowdin_string_delete`

Delete String · Destructive

Delete a source string.
Returns an empty response on success.
Use crowdin_string_delete to remove a key.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `string_id` (`integer`, required): String ID, from crowdin_strings_list. Example: 2814

Example input: `{"project_id":123456,"string_id":2814}`

### `crowdin_task_delete`

Delete Task · Destructive

Delete a task.
Returns an empty response on success.
Use crowdin_task_delete to remove a task.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `task_id` (`integer`, required): Task ID, from crowdin_tasks_list. Example: 2

Example input: `{"project_id":123456,"task_id":2}`

### `crowdin_translation_delete`

Delete Translation · Destructive

Delete one translation.
Returns an empty response on success.
Use crowdin_translation_delete to remove a wrong translation.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `project_id` (`integer`, required): Project ID, from crowdin_projects_list. Example: 123456
- `translation_id` (`integer`, required): Translation ID. Example: 190695

Example input: `{"project_id":123456,"translation_id":190695}`

## Related

Other Developer Tools connectors ([all 200](/agentkit/connectors/?category=developer-tools)):

- [GitHub](/agentkit/connectors/github/): Scalekit connector, OAuth, 217 tools
- [Datadog](/agentkit/connectors/datadog/): Scalekit connector, API key, 105 tools
- [Linear](/agentkit/connectors/linear/): Scalekit connector, OAuth, 64 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
