Unstructured API MCP Server

Data Science ToolsPython

Interact with Unstructured API to manage document processing workflows

Available Tools

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.

update_workflow

Update an existing workflow by params.

delete_workflow

Delete a specific workflow by id.

list_jobs

Lists jobs for a specific workflow from the Unstructured API.

get_job_info

Get detailed information about a specific job by job id.

cancel_job

Delete a specific job by id.

list_workflows_with_finished_jobs

Lists all workflows that have any completed job, together with information about source and destination details.

The Unstructured API MCP provides a comprehensive interface for managing document processing workflows through the Unstructured platform. It enables users to create, manage, and execute workflows that extract structured data from unstructured documents, connecting various source connectors (like S3, Azure) with destination systems (such as S3, Weaviate, and others). This MCP simplifies the process of document ingestion, processing, and data extraction for AI applications.

Unstructured API MCP

The Unstructured API MCP provides tools to interact with the Unstructured platform, allowing you to manage document processing workflows from various sources to destinations.

Installation

To install the Unstructured API MCP:

Clone the repository:

git clone https://github.com/Unstructured-IO/UNS-MCP.git
cd UNS-MCP

Install the package:

pip install -e .

Set up your environment variables by copying the template:

cp .env.template .env

Edit the .env file with your Unstructured API credentials and other required settings.

Configuration

To use this MCP with your AI assistant, you'll need to configure it in your client settings. Add the following configuration to your client:

{
  "mcpServers": {
    "unstructured-api": {
      "command": "python",
      "args": ["-m", "uns_mcp.server"]
    }
  }
}

Authentication

The MCP requires authentication with the Unstructured API. You'll need to obtain an API key from the Unstructured platform and set it in your environment variables.

Usage

Once installed and configured, you can use the MCP to:

Manage Source Connectors: Create, update, list, and delete connectors to document sources like S3, Azure, and Google Cloud.
Manage Destination Connectors: Set up destinations where processed documents will be sent, such as S3 buckets or vector databases like Weaviate.
Create and Run Workflows: Define workflows that connect sources to destinations with specific processing parameters, and execute these workflows to process documents.
Monitor Jobs: Track the status of processing jobs and retrieve information about completed jobs.

The MCP supports various source and destination connectors, with plans to add more in future updates. Refer to the Unstructured documentation for the complete list of supported connectors.

Examples

You can find example notebooks in the notebooks directory of the repository that demonstrate how to use the MCP for common document processing scenarios.

Troubleshooting

If you encounter issues:

Ensure your API credentials are correctly set in the environment variables
Check that the required dependencies are installed
Verify that your source and destination connectors are properly configured
Consult the Unstructured documentation for specific connector requirements