Unstructured MCP Server

Set up and interact with your unstructured data processing workflows in Unstructured Platform

Remote serverstreamable-httpPython

What is the Unstructured MCP server?

If you want an AI assistant working directly with Unstructured, the unstructured mcp server is the bridge. Set up and interact with your unstructured data processing workflows in Unstructured Platform.

What Unstructured does

An MCP server implementation for interacting with the Unstructured API. This server provides tools to list sources and workflows.

Tools it exposes

Once connected, the assistant can call these 14 tools directly:

  • list_sources — Lists available sources from the Unstructured API
  • get_source_info — Get detailed information about a specific source connector
  • create_source_connector — Create a source connector.)
  • update_source_connector — Update an existing source connector by params
  • delete_source_connector — Delete a source connector by source id
  • list_destinations — Lists available destinations from the Unstructured API
  • get_destination_info — Get detailed info about a specific destination connector
  • create_destination_connector — Create a destination connector by params
  • update_destination_connector — Update an existing destination connector by destination id
  • delete_destination_connector — Delete a destination connector by destination id
  • list_workflows — Lists workflows from the Unstructured API
  • get_workflow_info — Get detailed information about a specific workflow
  • create_workflow — Create a new workflow with source, destination id, etc
  • run_workflow — Run a specific workflow with workflow id

Installing the unstructured mcp server

The server is distributed via npm as @wonderwhy-er/desktop-commander, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 8 environment variables: UNSTRUCTURED_API_KEY, ANTHROPIC_API_KEY, WEAVIATE_CLOUD_API_KEY, FIRECRAWL_API_KEY, ASTRA_DB_APPLICATION_TOKEN, AZURE_ACCOUNT_KEY, AZURE_SAS_TOKEN, GOOGLEDRIVE_SERVICE_ACCOUNT_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  • Python 3.12+ - uv for environment management - An API key from Unstructured. You can sign up and obtain your API key here.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Unstructured sits in that group, and the shape of its toolset — list_sources, get_source_info, create_source_connector among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • With 14 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Unstructured.
  • Written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the unstructured mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
list_sourcesLists available sources from the Unstructured API.
get_source_infoGet detailed information about a specific source connector.
create_source_connectorCreate a source connector.)
update_source_connectorUpdate an existing source connector by params.
delete_source_connectorDelete a source connector by source id.
list_destinationsLists available destinations from the Unstructured API.
get_destination_infoGet detailed info about a specific destination connector
create_destination_connectorCreate a destination connector by params.
update_destination_connectorUpdate an existing destination connector by destination id.
delete_destination_connectorDelete a destination connector by destination id.
list_workflowsLists workflows from the Unstructured API.
get_workflow_infoGet detailed information about a specific workflow.
create_workflowCreate a new workflow with source, destination id, etc.
run_workflowRun a specific workflow with workflow id

How to install the Unstructured MCP server

Update your Claude Desktop config:
```json
{
  "mcpServers": {
    "UNS_MCP": {
      "command": "uvx",
      "args": ["uns_mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.12+ - uv for environment management - An API key from Unstructured. You can sign up and obtain your API key here.
VariableDescriptionRequired
UNSTRUCTURED_API_KEYCredential the server authenticates with.Yes
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
WEAVIATE_CLOUD_API_KEYCredential the server authenticates with.Yes
FIRECRAWL_API_KEYCredential the server authenticates with.Yes
ASTRA_DB_APPLICATION_TOKENCredential the server authenticates with.Yes
AZURE_ACCOUNT_KEYCredential the server authenticates with.Yes
AZURE_SAS_TOKENCredential the server authenticates with.Yes
GOOGLEDRIVE_SERVICE_ACCOUNT_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Unstructured to list sources.
  • Use Unstructured to get source info.
  • Use Unstructured to create source connector.

Frequently asked questions

It connects Unstructured to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (list_sources, get_source_info, create_source_connector, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Unstructured directly.