> **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 Dify

The Dify connector lets your AI agent act in each user's Dify account. Each user connects their own Dify access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 26 tools.

**Authentication:** Bearer Token
**Categories:** AI, Automation
**Tools:** 26: 14 read, 10 write, 2 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=DIFY)

## 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 Dify connection

   In **AgentKit > Connections**, create a Dify 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 = 'dify'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Dify:', 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: 'dify_annotations_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 = "dify"
   identifier = "user_123"

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

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

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Dify 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: 'dify_annotation_reply_status_get',
  toolInput: {
    action: 'enable',
    job_id: '<job_id>',
  },
  connector: 'dify',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="dify_annotation_reply_status_get",
    tool_input={
        "action": "enable",
        "job_id": "<job_id>",
    },
    connection_name="dify",
    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.

### `dify_annotation_reply_status_get`

Get Annotation Reply Job Status · Read-only

Get the status of an annotation reply enable or disable job.
Returns job_id, job_status (waiting, processing, completed, error) and error_msg.
Use this after dify_annotation_reply_configure.

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

Inputs:

- `action` (`string`, required): The action of the job: enable or disable. Example: enable. One of: `enable`, `disable`.
- `job_id` (`string`, required): Job ID returned by dify_annotation_reply_configure. Example: b15c8f68-1cf4-4877-bf21-ed7cf2011802.

Example input: `{"action":"enable","job_id":"<job_id>"}`

### `dify_annotations_list`

List Annotations · Read-only

List the app's annotations (saved question-answer pairs the app replies with directly when a question matches).
Returns data with each annotation's id, question, answer, hit_count and created_at, plus paging.
Use this to find an annotation ID.

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

Inputs:

- `keyword` (`string`, optional): Only annotations whose question or answer contains this text. Example: refund.
- `limit` (`integer`, optional): Items per page, up to 100. Defaults to 20. Example: 20.
- `page` (`integer`, optional): Page number. Defaults to 1. Example: 1.

Example input: `{}`

### `dify_app_feedbacks_list`

List App Feedback · Read-only

List all likes, dislikes and comments on the app's messages, from end users and admins.
Returns data with each feedback's message_id, rating, content, source and created_at.
Use this to review answer quality.

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

Inputs:

- `limit` (`integer`, optional): Items per page. Defaults to 20. Example: 20.
- `page` (`integer`, optional): Page number. Defaults to 1. Example: 1.

Example input: `{}`

### `dify_app_info_get`

Get App Info · Read-only

Get basic information about the Dify app this API key belongs to.
Returns name, description, tags, mode (chat, agent-chat, advanced-chat, workflow or completion) and author_name.
Use this first to know which run tool fits the app.

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

Inputs: none.

Example input: `{}`

### `dify_app_meta_get`

Get App Meta · Read-only

Get the display icons of the tools the app uses.
Returns tool_icons keyed by tool name.
Use this only when you need tool icons.

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

Inputs: none.

Example input: `{}`

### `dify_app_parameters_get`

Get App Parameters · Read-only

Get the app's input form and feature settings.
Returns opening_statement, suggested_questions, user_input_form (the input variables with their types and options), file upload limits and feature toggles.
Use this to build the inputs object for the run and send tools.

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

Inputs: none.

Example input: `{}`

### `dify_app_site_get`

Get App Web Settings · Read-only

Get the branding and display settings of the app's hosted web app.
Returns title, icon, theme color, description, copyright, privacy policy and default language.
Use this to mirror the app's branding.

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

Inputs: none.

Example input: `{}`

### `dify_conversation_variables_list`

List Conversation Variables · Read-only

List the variables stored in a conversation (Chatflow and Chatbot apps).
Returns data with each variable's id, name, value_type, value and description, plus has_more.
Use this to read conversation memory. Use dify_conversation_variable_update to change a value.

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

Inputs:

- `conversation_id` (`string`, required): Conversation ID, from dify_conversations_list or a chat response. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `last_id` (`string`, optional): Paging cursor: the id of the last variable on the previous page. Example: 3c5d7e9f-1a2b-4c6d-8e0f-2a4b6c8d0e1f.
- `limit` (`integer`, optional): Items per page. Defaults to 20. Example: 20.
- `user` (`string`, optional): End-user identifier you choose. Lists only that user's data. Example: user-123.
- `variable_name` (`string`, optional): Only the variable with this name. Example: customer_tier.

Example input: `{"conversation_id":"<conversation_id>"}`

### `dify_conversations_list`

List Conversations · Read-only

List an end user's conversations in a chat app, most recently active first.
Returns data with each conversation's id, name, inputs, status and timestamps, plus has_more and limit.
Use this to resume a conversation. Use dify_messages_list for its messages.

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

Inputs:

- `last_id` (`string`, optional): Paging cursor: the id of the last conversation on the previous page. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `limit` (`integer`, optional): Items per page. Defaults to 20. Example: 20.
- `sort_by` (`string`, optional): Sort field; prefix - for descending. Defaults to -updated_at. Example: -updated_at. One of: `created_at`, `-created_at`, `updated_at`, `-updated_at`.
- `user` (`string`, optional): End-user identifier you choose. Lists only that user's data. Example: user-123.

Example input: `{}`

### `dify_end_user_get`

Get End User · Read-only

Get an end user's details by Dify end-user ID.
Returns the end user's id, type, session_id (your user identifier) and timestamps.
Use this to resolve an end-user ID returned by another call.

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

Inputs:

- `end_user_id` (`string`, required): Dify end-user ID, as returned in conversation or log data. Example: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d.

Example input: `{"end_user_id":"<end_user_id>"}`

### `dify_message_suggested_questions_get`

Get Suggested Questions · Read-only

Get the follow-up questions Dify suggests after a message.
Returns data, a list of suggested question strings (empty when none).
Use this to offer next questions in a chat.

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

Inputs:

- `message_id` (`string`, required): Message ID, from dify_messages_list or a chat response. Example: 9da23599-e713-473b-982c-4328d4f5c78a.
- `user` (`string`, required): End-user identifier you choose. Lists only that user's data. Example: user-123.

Example input: `{"message_id":"<message_id>","user":"<user>"}`

### `dify_messages_list`

List Conversation Messages · Read-only

Get a conversation's message history, newest first.
Returns data with each message's id, query, answer, feedback, attached files and created_at, plus has_more.
Pass first_id to page back to older messages.

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

Inputs:

- `conversation_id` (`string`, required): Conversation to read, from dify_conversations_list. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `first_id` (`string`, optional): Paging cursor: the id of the first (oldest) message on the current page, to get older ones. Example: 9da23599-e713-473b-982c-4328d4f5c78a.
- `limit` (`integer`, optional): Messages to return. Defaults to 20. Example: 20.
- `user` (`string`, optional): End-user identifier you choose. Lists only that user's data. Example: user-123.

Example input: `{"conversation_id":"<conversation_id>"}`

### `dify_workflow_logs_list`

List Workflow Logs · Read-only

List past workflow runs of the app, newest first, with filters.
Returns data with each run's id, status, error, elapsed time, tokens, steps and creator, plus page, limit, total and has_more.
Use this to audit or debug runs. Use dify_workflow_run_get for one run's outputs.

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

Inputs:

- `created_at_after` (`string`, optional): Only runs created after this ISO 8601 time. Example: 2026-11-01T00:00:00Z.
- `created_at_before` (`string`, optional): Only runs created before this ISO 8601 time. Example: 2026-11-30T23:59:59Z.
- `created_by_account` (`string`, optional): Only runs started by this Dify account email. Example: name@example.com.
- `created_by_end_user_session_id` (`string`, optional): Only runs started by this end-user session ID. Example: user-123.
- `keyword` (`string`, optional): Text to search for in the logs. Example: invoice.
- `limit` (`integer`, optional): Items per page. Defaults to 20. Example: 20.
- `page` (`integer`, optional): Page number. Defaults to 1. Example: 1.
- `status` (`string`, optional): Only runs with this result. Example: failed. One of: `succeeded`, `failed`, `stopped`.

Example input: `{}`

### `dify_workflow_run_get`

Get Workflow Run · Read-only

Get one workflow run's status, inputs, outputs and metrics.
Returns id, workflow_id, status (running, succeeded, failed, stopped), inputs, outputs, error, total_steps, total_tokens, created_at and finished_at.
Use this for Workflow and Chatflow apps.

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

Inputs:

- `workflow_run_id` (`string`, required): Workflow run ID, from dify_workflow_run or dify_workflow_logs_list. Example: fb47b2e6-5e3b-4c8e-9a43-2f5e7d0c1a9b.

Example input: `{"workflow_run_id":"<workflow_run_id>"}`

### `dify_annotation_create`

Create Annotation · Write

Add an annotation: a question and the exact answer the app should return when a user asks something matching.
Returns the new annotation with its id.
Annotation reply must be enabled (dify_annotation_reply_configure) for it to be used.

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

Inputs:

- `answer` (`string`, required): Answer to return. Example: You can request a full refund within 30 days.
- `question` (`string`, required): Question to match. Example: What is your refund policy?.

Example input: `{"answer":"<answer>","question":"<question>"}`

### `dify_annotation_reply_configure`

Configure Annotation Reply · Write

Turn annotation reply on or off for the app, with the embedding model and match threshold. Runs as a background job.
Returns job_id and job_status.
Check progress with dify_annotation_reply_status_get.

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

Inputs:

- `action` (`string`, required): enable or disable. Example: enable. One of: `enable`, `disable`.
- `embedding_model_name` (`string`, required): Embedding model used to match questions. Example: text-embedding-3-small.
- `embedding_provider_name` (`string`, required): Embedding model provider. Example: openai.
- `score_threshold` (`number`, required): Minimum similarity (0 to 1) for an annotation to match. Example: 0.9.

Example input: `{"action":"enable","embedding_model_name":"<embedding_model_name>","embedding_provider_name":"<embedding_provider_name>","score_threshold":0.9}`

### `dify_annotation_update`

Update Annotation · Write

Replace an annotation's question and answer.
Returns the updated annotation.
Send both fields.

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

Inputs:

- `annotation_id` (`string`, required): Annotation ID from dify_annotations_list. Example: 69d48372-ad81-4c75-9c46-2ce197b4d402.
- `answer` (`string`, required): New answer. Example: Refunds are available within 45 days.
- `question` (`string`, required): New question. Example: What is your refund policy?.

Example input: `{"annotation_id":"<annotation_id>","answer":"<answer>","question":"<question>"}`

### `dify_chat_message_send`

Send Chat Message · Write

Send a user message to a Dify chat app (Chatbot, Chatflow or Agent) and wait for the full reply.
Returns answer, conversation_id, message_id, metadata (token usage, retriever resources) and created_at.
Send the returned conversation_id with the next message to continue the conversation. Agent apps that only stream may reject blocking calls.

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

Inputs:

- `inputs` (`object`, required): Values for the app's input variables, keyed by variable name. Get the names and types from user_input_form in dify_app_parameters_get. Send {} when the app has none. Example: {"topic": "pricing"}
- `query` (`string`, required): The user's message. Example: What are your support hours?.
- `user` (`string`, required): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.
- `auto_generate_name` (`boolean`, optional): Generate a conversation title automatically. Defaults to true. Example: true.
- `conversation_id` (`string`, optional): Conversation to continue. Leave out to start a new one. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `files` (`array`, optional): Files to attach, each with type (image, document, audio, video), transfer_method remote_url and url. Only for apps whose model accepts files. Example: [{"type": "image", "transfer_method": "remote_url", "url": "https://example.com/photo.png"}]
- `workflow_id` (`string`, optional): Chatflow apps only: published workflow version to run instead of the latest. Example: b6e9c6f4-3a0e-4f7a-9c1d-2e8b7a6c5d4e.

Example input: `{"inputs":{"topic":"pricing"},"query":"<query>","user":"<user>"}`

### `dify_completion_message_send`

Send Completion Message · Write

Run a Dify Text Generator app once with the given inputs and wait for the generated text.
Returns answer, message_id, metadata (token usage) and created_at.
Use this for text generator apps. Use dify_chat_message_send for chat apps and dify_workflow_run for workflow apps.

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

Inputs:

- `inputs` (`object`, required): Values for the app's input variables, keyed by variable name. Get the names and types from user_input_form in dify_app_parameters_get. Send {} when the app has none. Example: {"topic": "pricing"}
- `user` (`string`, required): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.
- `files` (`array`, optional): Files to attach, each with type (image, document, audio, video), transfer_method remote_url and url. Only for apps whose model accepts files. Example: [{"type": "image", "transfer_method": "remote_url", "url": "https://example.com/photo.png"}]
- `query` (`string`, optional): Text to process, for older apps that take it outside inputs. Example: Summarize this paragraph...

Example input: `{"inputs":{"topic":"pricing"},"user":"<user>"}`

### `dify_conversation_rename`

Rename Conversation · Write

Rename a conversation, or let Dify generate a name from its messages.
Returns the conversation with its new name.
Send name, or auto_generate true.

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

Inputs:

- `conversation_id` (`string`, required): Conversation ID, from dify_conversations_list or a chat response. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `auto_generate` (`boolean`, optional): Generate the name automatically; name is then ignored. Example: false.
- `name` (`string`, optional): New name. Needed unless auto_generate is true. Example: Pricing questions.
- `user` (`string`, optional): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.

Example input: `{"conversation_id":"<conversation_id>"}`

### `dify_conversation_variable_update`

Update Conversation Variable · Write

Set a conversation variable's value. The value must match the variable's type.
Returns the updated variable.
Use dify_conversation_variables_list to find variable IDs and types.

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

Inputs:

- `conversation_id` (`string`, required): Conversation ID, from dify_conversations_list or a chat response. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `value` (`string`, required): New value, of the variable's type (string, number, object or array). Example: gold.
- `variable_id` (`string`, required): Variable ID from dify_conversation_variables_list. Example: 3c5d7e9f-1a2b-4c6d-8e0f-2a4b6c8d0e1f.
- `user` (`string`, optional): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.

Example input: `{"conversation_id":"<conversation_id>","value":"<value>","variable_id":"<variable_id>"}`

### `dify_message_feedback_submit`

Submit Message Feedback · Write

Like or dislike a message, with an optional comment, or revoke earlier feedback.
Returns result success.
Set rating to null to remove feedback. The user must be the one who received the message.

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

Inputs:

- `message_id` (`string`, required): Message ID, from dify_messages_list or a chat response. Example: 9da23599-e713-473b-982c-4328d4f5c78a.
- `user` (`string`, required): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.
- `content` (`string`, optional): Optional text feedback. Example: Very helpful, thanks.
- `rating` (`string`, optional): like or dislike; null revokes earlier feedback. Example: like. One of: `like`, `dislike`.

Example input: `{"message_id":"<message_id>","user":"<user>"}`

### `dify_workflow_run`

Run Workflow · Write

Run a Dify Workflow app's published workflow with the given inputs and wait for it to finish.
Returns workflow_run_id, task_id and data with status, outputs, error, elapsed_time and total_tokens.
Use dify_workflow_run_get to read a run later. Use dify_workflow_run_by_id to run a specific version.

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

Inputs:

- `inputs` (`object`, required): Values for the app's input variables, keyed by variable name. Get the names and types from user_input_form in dify_app_parameters_get. Send {} when the app has none. Example: {"topic": "pricing"}
- `user` (`string`, required): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.
- `files` (`array`, optional): Files to attach, each with type (image, document, audio, video), transfer_method remote_url and url. Only for apps whose model accepts files. Example: [{"type": "image", "transfer_method": "remote_url", "url": "https://example.com/photo.png"}]

Example input: `{"inputs":{"topic":"pricing"},"user":"<user>"}`

### `dify_workflow_run_by_id`

Run Workflow Version · Write

Run a specific published version of a Dify Workflow app's workflow and wait for it to finish.
Returns workflow_run_id, task_id and data with status, outputs, error and timings.
Use dify_workflow_run to run the latest published version.

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

Inputs:

- `inputs` (`object`, required): Values for the app's input variables, keyed by variable name. Get the names and types from user_input_form in dify_app_parameters_get. Send {} when the app has none. Example: {"topic": "pricing"}
- `user` (`string`, required): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.
- `workflow_id` (`string`, required): Published workflow version ID, from a previous run's workflow_id or dify_workflow_run_get. Example: b6e9c6f4-3a0e-4f7a-9c1d-2e8b7a6c5d4e.
- `files` (`array`, optional): Files to attach, each with type (image, document, audio, video), transfer_method remote_url and url. Only for apps whose model accepts files. Example: [{"type": "image", "transfer_method": "remote_url", "url": "https://example.com/photo.png"}]

Example input: `{"inputs":{"topic":"pricing"},"user":"<user>","workflow_id":"<workflow_id>"}`

### `dify_annotation_delete`

Delete Annotation · Destructive

Delete an annotation and its hit history.
Returns no content on success.
Use dify_annotations_list to find IDs.

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

Inputs:

- `annotation_id` (`string`, required): Annotation ID from dify_annotations_list. Example: 69d48372-ad81-4c75-9c46-2ce197b4d402.

Example input: `{"annotation_id":"<annotation_id>"}`

### `dify_conversation_delete`

Delete Conversation · Destructive

Delete a conversation.
Returns no content on success.
Use dify_conversations_list to find IDs.

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

Inputs:

- `conversation_id` (`string`, required): Conversation ID, from dify_conversations_list or a chat response. Example: 45701982-8118-4bc5-8e9b-64562b4555f2.
- `user` (`string`, optional): End-user identifier you choose, unique within your app. Conversations, messages and files are only visible to calls with the same user. Example: user-123.

Example input: `{"conversation_id":"<conversation_id>"}`

## Related

Other AI connectors ([all 216](/agentkit/connectors/?category=ai)):

- [Chorus](/agentkit/connectors/chorus/): Scalekit connector, Username and password, 9 tools
- [Gong](/agentkit/connectors/gong/): Scalekit connector, OAuth, 69 tools
- [Jiminny](/agentkit/connectors/jiminny/): Scalekit connector, Access token, 27 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 |
