> **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 Unstructured

The Unstructured connector lets your AI agent act in each user's Unstructured account. Each user connects their own Unstructured API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 30 tools.

**Authentication:** API Key
**Categories:** AI, Files & Documents
**Tools:** 30: 17 read, 10 write, 3 destructive
**Users sign in with:** API key
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=UNSTRUCTURED)

## 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 Unstructured connection

   In **AgentKit > Connections**, create an Unstructured 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 = 'unstructured'
   const identifier = 'user_123'

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

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

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

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Unstructured 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: 'unstructured_account_get',
  toolInput: {},
  connector: 'unstructured',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="unstructured_account_get",
    tool_input={},
    connection_name="unstructured",
    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.

### `unstructured_account_get`

Get Account · Read-only

Get the account and workspace the API key belongs to.
Returns account_id and workspace_id.
Use this to confirm which workspace the connection works in.

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

Inputs: none.

Example input: `{}`

### `unstructured_destination_connection_check_get`

Get Destination Connection Check · Read-only

Get the latest connection check for a destination connector.
Returns id, status (SCHEDULED, SUCCESS or FAILURE), reason when it failed, and timestamps.
Use this after unstructured_destination_connection_check_create.

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

Inputs:

- `destination_id` (`string`, required): Destination connector ID (UUID) or key. Get it from unstructured_destinations_list. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a

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

### `unstructured_destination_get`

Get Destination Connector · Read-only

Get one destination connector by ID or key.
Returns id, key, name, type, config (secrets masked), created_at and updated_at.
Use unstructured_destinations_list to find the ID.

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

Inputs:

- `destination_id` (`string`, required): Destination connector ID (UUID) or key. Get it from unstructured_destinations_list. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a

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

### `unstructured_destinations_list`

List Destination Connectors · Read-only

List the workspace's destination connectors, optionally filtered by type.
Returns an array of connectors with id, key, name, type, config (secrets masked) and created_at.
Use this to find a destination ID for a workflow. Use unstructured_destination_get for one connector.

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

Inputs:

- `destination_type` (`string`, optional): Only destination connectors of this type, for example astradb, couchbase, databricks_volumes, databricks_volume_delta_tables, delta_table, elasticsearch. Example: s3. One of: `astradb`, `couchbase`, `databricks_volumes`, `databricks_volume_delta_tables`, `delta_table`, `elasticsearch`, `kafka-cloud`, `milvus`, `mongodb`, `motherduck`, `neo4j`, `onedrive`, `pinecone`, `postgres`, `redis`, `qdrant-cloud`, `snowflake`, `teradata`, `weaviate-cloud`, `ibm_watsonx_s3`, `s3`, `azure`, `gcs`.

Example input: `{}`

### `unstructured_job_details_get`

Get Job Details · Read-only

Get a job's processing details per node.
Returns processing_status, progress, node_stats (per-node document counts), summary and warning_nodes.
Use this to see where documents are in the pipeline or which step failed.

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

Inputs:

- `job_id` (`string`, required): Job ID (UUID) from unstructured_workflow_run or unstructured_jobs_list. Example: 3e5a7c9b-1d2f-4a6c-8e0b-2d4f6a8c0e1d

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

### `unstructured_job_failed_files_list`

List Job Failed Files · Read-only

List the documents that failed in a job, with their error messages.
Returns failed_files (each document with its error), total and next_offset.
Use this to debug a run that reported failures.

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

Inputs:

- `job_id` (`string`, required): Job ID (UUID) from unstructured_workflow_run or unstructured_jobs_list. Example: 3e5a7c9b-1d2f-4a6c-8e0b-2d4f6a8c0e1d
- `limit` (`integer`, optional): Files per page, 1 to 1000. Example: 100
- `offset` (`integer`, optional): Files to skip, for paging. Example: 0

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

### `unstructured_job_file_status_get`

Get Job File Status · Read-only

Get the processing status of each file in a job, with any warnings.
Returns files (each with its id, name, status and notices) and truncated.
Use this to get file IDs for unstructured_job_output_download or to review warnings.

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

Inputs:

- `job_id` (`string`, required): Job ID (UUID) from unstructured_workflow_run or unstructured_jobs_list. Example: 3e5a7c9b-1d2f-4a6c-8e0b-2d4f6a8c0e1d
- `has_warnings` (`boolean`, optional): true returns only files with notices, false only files without. Leave empty for every file. Example: true

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

### `unstructured_job_get`

Get Job · Read-only

Get a job's status.
Returns id, workflow_id, status, runtime, created_at, failed_file_count, input_file_ids and output_node_files.
Use this to poll a run. Use unstructured_job_details_get for per-node counts and unstructured_job_failed_files_list for errors.

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

Inputs:

- `job_id` (`string`, required): Job ID (UUID) from unstructured_workflow_run or unstructured_jobs_list. Example: 3e5a7c9b-1d2f-4a6c-8e0b-2d4f6a8c0e1d

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

### `unstructured_job_output_download`

Download Job Output · Read-only

Get the processed output of one file from a job, as Unstructured document elements.
Returns a JSON array of elements with type, text, element_id and metadata (and embeddings when the workflow embeds).
Use this to read results without opening the destination. Get file IDs from unstructured_job_file_status_get.

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

Inputs:

- `file_id` (`string`, required): ID of the processed file, from unstructured_job_get (input_file_ids) or unstructured_job_file_status_get. Example: 9a1b3c5d7e
- `job_id` (`string`, required): Job ID (UUID) from unstructured_workflow_run or unstructured_jobs_list. Example: 3e5a7c9b-1d2f-4a6c-8e0b-2d4f6a8c0e1d
- `node_id` (`string`, optional): Node whose output to return. Defaults to the last processing node. Example: 5d7f9b1c-3e5a-4c7e-9a1b-3c5d7e9f1a2b

Example input: `{"file_id":"<file_id>","job_id":"<job_id>"}`

### `unstructured_jobs_list`

List Jobs · Read-only

List jobs (workflow runs) in the workspace, optionally for one workflow or status.
Returns an array of jobs with id, workflow_id, workflow_name, status, runtime and created_at.
Use this to find recent runs. Use unstructured_job_get for one job.

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

Inputs:

- `status` (`string`, optional): Only jobs in this status, for example SCHEDULED, IN_PROGRESS, COMPLETED, STOPPED or FAILED. Example: COMPLETED
- `workflow_id` (`string`, optional): Only jobs of this workflow. Example: f0a1b2c3-4d5e-4f7a-8b9c-0d1e2f3a4b5c

Example input: `{}`

### `unstructured_source_connection_check_get`

Get Source Connection Check · Read-only

Get the latest connection check for a source connector.
Returns id, status (SCHEDULED, SUCCESS or FAILURE), reason when it failed, and timestamps.
Use this after unstructured_source_connection_check_create.

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

Inputs:

- `source_id` (`string`, required): Source connector ID (UUID) or key. Get it from unstructured_sources_list. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b

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

### `unstructured_source_get`

Get Source Connector · Read-only

Get one source connector by ID or key.
Returns id, key, name, type, config (secrets masked), created_at and updated_at.
Use unstructured_sources_list to find the ID.

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

Inputs:

- `source_id` (`string`, required): Source connector ID (UUID) or key. Get it from unstructured_sources_list. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b

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

### `unstructured_sources_list`

List Source Connectors · Read-only

List the workspace's source connectors, optionally filtered by type.
Returns an array of connectors with id, key, name, type, config (secrets masked) and created_at.
Use this to find a source ID for a workflow. Use unstructured_source_get for one connector.

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

Inputs:

- `source_type` (`string`, optional): Only source connectors of this type, for example confluence, couchbase, databricks_volumes, dropbox, elasticsearch, google_drive. Example: s3. One of: `confluence`, `couchbase`, `databricks_volumes`, `dropbox`, `elasticsearch`, `google_drive`, `kafka-cloud`, `mongodb`, `onedrive`, `outlook`, `postgres`, `salesforce`, `sharepoint`, `slack`, `snowflake`, `teradata`, `jira`, `zendesk`, `s3`, `azure`, `gcs`.

Example input: `{}`

### `unstructured_template_get`

Get Workflow Template · Read-only

Get a workflow template with its nodes.
Returns id, name, version, description and nodes (each with name, type, subtype and settings).
Use this to copy node settings into a custom workflow.

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

Inputs:

- `template_id` (`string`, required): Template ID from unstructured_templates_list. Example: hi-res-and-enrich

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

### `unstructured_templates_list`

List Workflow Templates · Read-only

List the workflow templates Unstructured provides.
Returns templates with id, name, version, description and last_updated.
Use this to pick a template_id for unstructured_workflow_create.

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

Inputs: none.

Example input: `{}`

### `unstructured_workflow_get`

Get Workflow · Read-only

Get one workflow by ID or key, including its processing nodes.
Returns id, key, name, sources, destinations, workflow_type, workflow_nodes, schedule, status and timestamps.
Use this to inspect or copy a workflow's node settings. Use unstructured_workflows_list to find the ID.

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

Inputs:

- `workflow_id` (`string`, required): Workflow ID (UUID) or key. Get it from unstructured_workflows_list. Example: f0a1b2c3-4d5e-4f7a-8b9c-0d1e2f3a4b5c

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

### `unstructured_workflows_list`

List Workflows · Read-only

List the workspace's workflows, optionally filtered by connector, state, name or creation time.
Returns an array of workflows with id, key, name, sources, destinations, workflow_type, schedule, status and created_at.
Use this to find a workflow to run. Use unstructured_workflow_get for its nodes.

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

Inputs:

- `created_before` (`string`, optional): Only workflows created before this time (ISO 8601). Example: 2026-11-15T00:00:00Z
- `created_since` (`string`, optional): Only workflows created at or after this time (ISO 8601). Example: 2026-10-01T00:00:00Z
- `destination_id` (`string`, optional): Only workflows that write to this destination connector. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a
- `name` (`string`, optional): Only workflows with this name. Example: Invoice pipeline
- `page` (`integer`, optional): Page number, starting at 1. Example: 1
- `page_size` (`integer`, optional): Workflows per page. Example: 20
- `sort_by` (`string`, optional): Field to sort by. Default: id. Example: created_at
- `sort_direction` (`string`, optional): Sort direction: asc or desc. Example: desc. One of: `asc`, `desc`.
- `source_id` (`string`, optional): Only workflows that read from this source connector. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b
- `status` (`string`, optional): Workflow state: active or inactive. Example: active. One of: `active`, `inactive`.

Example input: `{}`

### `unstructured_destination_connection_check_create`

Check Destination Connection · Write

Start a check that the destination connector can reach its service with its credentials.
Returns the check with id, status (SCHEDULED, SUCCESS or FAILURE) and created_at.
Use this after creating or updating a connector, then read the outcome with unstructured_destination_connection_check_get.

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

Inputs:

- `destination_id` (`string`, required): Destination connector ID (UUID) or key. Get it from unstructured_destinations_list. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a

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

### `unstructured_destination_create`

Create Destination Connector · Write

Create a destination connector that lets workflows write processed output to a storage service, database or vector store, using the type's connection settings.
Returns the connector with id, key, name, type and config.
Use this before unstructured_workflow_create. Run unstructured_destination_connection_check_create afterwards to test the credentials.

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

Inputs:

- `config` (`object`, required): Connection settings for the chosen type. For s3: remote_url (s3://bucket/path/) plus key and secret; vector stores and databases take their own fields (for example api_endpoint, token and collection_name for astradb). See https://docs.unstructured.io/api-reference/workflow/destinations/overview for each type's fields. Example: {"remote_url": "s3://acme-docs/processed/", "key": "AKIAIOSFODNN7EXAMPLE", "secret": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"}
- `name` (`string`, required): Display name for the connector. Example: Processed output bucket
- `type` (`string`, required): Connector type, such as astradb, couchbase, databricks_volumes, databricks_volume_delta_tables, delta_table, elasticsearch, kafka-cloud, milvus, mongodb, motherduck, neo4j, onedrive, pinecone, postgres, redis, qdrant-cloud, snowflake, teradata, weaviate-cloud, ibm_watsonx_s3, s3, azure, gcs. The type decides which config fields are needed. Example: s3. One of: `astradb`, `couchbase`, `databricks_volumes`, `databricks_volume_delta_tables`, `delta_table`, `elasticsearch`, `kafka-cloud`, `milvus`, `mongodb`, `motherduck`, `neo4j`, `onedrive`, `pinecone`, `postgres`, `redis`, `qdrant-cloud`, `snowflake`, `teradata`, `weaviate-cloud`, `ibm_watsonx_s3`, `s3`, `azure`, `gcs`.
- `key` (`string`, optional): Stable identifier for the destination, unique in the workspace: 1-63 lowercase letters, digits and hyphens. Derived from name if empty. Example: s3-invoices

Example input: `{"config":{"remote_url":"s3://acme-docs/processed/","key":"AKIAIOSFODNN7EXAMPLE","secret":"wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"},"name":"<name>","type":"astradb"}`

### `unstructured_destination_update`

Update Destination Connector · Write

Replace a destination connector's connection settings, and optionally rename it.
Returns the updated connector.
Use this to rotate credentials or change the path. Use unstructured_destination_connection_check_create to test it afterwards.

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

Inputs:

- `config` (`object`, required): Full connection settings for the connector's type; they replace the current config. Example: {"remote_url": "s3://acme-docs/processed/", "key": "AKIAIOSFODNN7EXAMPLE", "secret": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"}
- `destination_id` (`string`, required): Destination connector ID (UUID) or key. Get it from unstructured_destinations_list. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a
- `key` (`string`, optional): New key, unique in the workspace. Requests using the old key then return 404. Example: s3-invoices-eu
- `name` (`string`, optional): New display name. Leave empty to keep it. Example: Invoices bucket (EU)

Example input: `{"config":{"remote_url":"s3://acme-docs/processed/","key":"AKIAIOSFODNN7EXAMPLE","secret":"wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"},"destination_id":"<destination_id>"}`

### `unstructured_job_cancel`

Cancel Job · Write

Request that a scheduled or running job stop.
Returns the job with stop_requested set.
Use this to stop a run. Poll unstructured_job_get until the status is final.

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

Inputs:

- `job_id` (`string`, required): Job ID (UUID) from unstructured_workflow_run or unstructured_jobs_list. Example: 3e5a7c9b-1d2f-4a6c-8e0b-2d4f6a8c0e1d

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

### `unstructured_source_connection_check_create`

Check Source Connection · Write

Start a check that the source connector can reach its service with its credentials.
Returns the check with id, status (SCHEDULED, SUCCESS or FAILURE) and created_at.
Use this after creating or updating a connector, then read the outcome with unstructured_source_connection_check_get.

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

Inputs:

- `source_id` (`string`, required): Source connector ID (UUID) or key. Get it from unstructured_sources_list. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b

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

### `unstructured_source_create`

Create Source Connector · Write

Create a source connector that lets workflows read documents from a storage service, drive or app, using the type's connection settings.
Returns the connector with id, key, name, type and config.
Use this before unstructured_workflow_create. Run unstructured_source_connection_check_create afterwards to test the credentials.

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

Inputs:

- `config` (`object`, required): Connection settings for the chosen type. For s3: remote_url (s3://bucket/path/) plus key and secret, or anonymous true for a public bucket; gcs and azure use a remote_url too; other types take their own fields (for example a site URL and client credentials for sharepoint). See https://docs.unstructured.io/api-reference/workflow/sources/overview for each type's fields. Example: {"remote_url": "s3://acme-docs/invoices/", "key": "AKIAIOSFODNN7EXAMPLE", "secret": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY", "recursive": true}
- `name` (`string`, required): Display name for the connector. Example: Invoices bucket
- `type` (`string`, required): Connector type, such as confluence, couchbase, databricks_volumes, dropbox, elasticsearch, google_drive, kafka-cloud, mongodb, onedrive, outlook, postgres, salesforce, sharepoint, slack, snowflake, teradata, jira, zendesk, s3, azure, gcs. The type decides which config fields are needed. Example: s3. One of: `confluence`, `couchbase`, `databricks_volumes`, `dropbox`, `elasticsearch`, `google_drive`, `kafka-cloud`, `mongodb`, `onedrive`, `outlook`, `postgres`, `salesforce`, `sharepoint`, `slack`, `snowflake`, `teradata`, `jira`, `zendesk`, `s3`, `azure`, `gcs`.
- `key` (`string`, optional): Stable identifier for the source, unique in the workspace: 1-63 lowercase letters, digits and hyphens. Derived from name if empty. Example: s3-invoices

Example input: `{"config":{"remote_url":"s3://acme-docs/invoices/","key":"AKIAIOSFODNN7EXAMPLE","secret":"wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY","recursive":true},"name":"<name>","type":"confluence"}`

### `unstructured_source_update`

Update Source Connector · Write

Replace a source connector's connection settings, and optionally rename it.
Returns the updated connector.
Use this to rotate credentials or change the path. Use unstructured_source_connection_check_create to test it afterwards.

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

Inputs:

- `config` (`object`, required): Full connection settings for the connector's type; they replace the current config. Example: {"remote_url": "s3://acme-docs/invoices/", "key": "AKIAIOSFODNN7EXAMPLE", "secret": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY", "recursive": true}
- `source_id` (`string`, required): Source connector ID (UUID) or key. Get it from unstructured_sources_list. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b
- `key` (`string`, optional): New key, unique in the workspace. Requests using the old key then return 404. Example: s3-invoices-eu
- `name` (`string`, optional): New display name. Leave empty to keep it. Example: Invoices bucket (EU)

Example input: `{"config":{"remote_url":"s3://acme-docs/invoices/","key":"AKIAIOSFODNN7EXAMPLE","secret":"wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY","recursive":true},"source_id":"<source_id>"}`

### `unstructured_workflow_create`

Create Workflow · Write

Create a workflow that reads documents from a source connector, partitions and optionally enriches, chunks and embeds them, and writes the output to a destination connector.
Returns the workflow with id, key, name, workflow_type, nodes and schedule.
Use this after creating connectors. Start it with unstructured_workflow_run or give it a schedule.

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

Inputs:

- `name` (`string`, required): Workflow name. Example: Invoice pipeline
- `workflow_type` (`string`, required): basic, advanced or platinum use Unstructured's preset processing; custom uses workflow_nodes or template_id. Example: custom. One of: `basic`, `advanced`, `platinum`, `custom`.
- `destination_id` (`string`, optional): Destination connector to write to. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a
- `key` (`string`, optional): Stable identifier for the workflow, unique in the workspace: 1-63 lowercase letters, digits and hyphens. Derived from name if empty. Example: invoice-pipeline
- `reprocess_all` (`boolean`, optional): If true, the next runs reprocess every document, not only new or changed ones. Example: false
- `schedule` (`string`, optional): How often to run automatically, for example every hour, daily or weekly. Leave empty to run only on demand. Example: daily. One of: `every 15 minutes`, `every hour`, `every 2 hours`, `every 4 hours`, `every 6 hours`, `every 8 hours`, `every 10 hours`, `every 12 hours`, `daily`, `weekly`, `monthly`.
- `source_id` (`string`, optional): Source connector to read from. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b
- `template_id` (`string`, optional): Template to build a custom workflow from instead of workflow_nodes. Get IDs from unstructured_templates_list. Example: hi-res-and-enrich
- `workflow_nodes` (`array`, optional): For custom workflows: processing nodes in order (partition, then optional enrichment, chunk, embed or extract), each with name, type, subtype and settings. Copy node shapes from unstructured_template_get or an existing workflow. Example: [{"name": "Partitioner", "type": "partition", "subtype": "unstructured_api", "settings": {"strategy": "fast"}}]

Example input: `{"name":"<name>","workflow_type":"basic"}`

### `unstructured_workflow_run`

Run Workflow · Write

Start a job that runs a workflow now, reading all new or changed documents from its source connector, spending processing credits.
Returns the job with id, workflow_id, status and created_at. A new job starts only if none is already active for the workflow.
Use this for on-demand runs of workflows that have a source connector. Follow the job with unstructured_job_get.

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

Inputs:

- `workflow_id` (`string`, required): Workflow ID (UUID) or key. Get it from unstructured_workflows_list. Example: f0a1b2c3-4d5e-4f7a-8b9c-0d1e2f3a4b5c

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

### `unstructured_workflow_update`

Update Workflow · Write

Change a workflow's name, connectors, type, nodes or schedule, or pause and resume it.
Returns the updated workflow.
Use this to adjust processing. Changing settings does not reprocess existing documents unless reprocess_all is true.

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

Inputs:

- `workflow_id` (`string`, required): Workflow ID (UUID) or key. Get it from unstructured_workflows_list. Example: f0a1b2c3-4d5e-4f7a-8b9c-0d1e2f3a4b5c
- `destination_id` (`string`, optional): New destination connector. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a
- `name` (`string`, optional): New name. Example: Invoice pipeline v2
- `reprocess_all` (`boolean`, optional): If true, the next runs reprocess every document. Example: true
- `schedule` (`string`, optional): New run schedule. Example: weekly. One of: `every 15 minutes`, `every hour`, `every 2 hours`, `every 4 hours`, `every 6 hours`, `every 8 hours`, `every 10 hours`, `every 12 hours`, `daily`, `weekly`, `monthly`.
- `source_id` (`string`, optional): New source connector. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b
- `state` (`string`, optional): active to enable scheduled runs, inactive to pause them. Example: inactive. One of: `active`, `inactive`.
- `workflow_nodes` (`array`, optional): Replacement processing nodes for a custom workflow. Example: [{"name": "Partitioner", "type": "partition", "subtype": "unstructured_api", "settings": {"strategy": "fast"}}]
- `workflow_type` (`string`, optional): New workflow type: basic, advanced, platinum or custom. Example: custom. One of: `basic`, `advanced`, `platinum`, `custom`.

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

### `unstructured_destination_delete`

Delete Destination Connector · Destructive

Delete a destination connector.
Returns a confirmation.
Remove it from workflows first; workflows that still use it cannot run.

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

Inputs:

- `destination_id` (`string`, required): Destination connector ID (UUID) or key. Get it from unstructured_destinations_list. Example: 7c9e1a3b-5d7f-4b2c-8e4a-6f8b0d2c4e6a

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

### `unstructured_source_delete`

Delete Source Connector · Destructive

Delete a source connector.
Returns a confirmation.
Remove it from workflows first; workflows that still use it cannot run.

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

Inputs:

- `source_id` (`string`, required): Source connector ID (UUID) or key. Get it from unstructured_sources_list. Example: 2b4f6d8e-1a3c-4e5f-9a7b-0c2d4e6f8a1b

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

### `unstructured_workflow_delete`

Delete Workflow · Destructive

Delete a workflow. Its connectors stay.
Returns a confirmation.
Use unstructured_workflow_update with state inactive to pause it instead.

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

Inputs:

- `workflow_id` (`string`, required): Workflow ID (UUID) or key. Get it from unstructured_workflows_list. Example: f0a1b2c3-4d5e-4f7a-8b9c-0d1e2f3a4b5c

Example input: `{"workflow_id":"<workflow_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 |
