This is Unstructured's official MCP server for the Unstructured API, covering full management of sources, destinations, workflows, and jobs, plus integrated Firecrawl web crawling, with stdio and SSE transports and a Claude Desktop configuration example. The README explicitly states the server is not actively maintained and is kept for reference, recommending the Unstructured Transform MCP server for file parsing and structured transformation. It suits users who already have an Unstructured API key and want to manage connectors and workflows through MCP; it is not suited for production use requiring active maintenance, and delete tools plus the full-replacement behavior of update_workflow require caution.
Strongest · Documentation 11/20 Weakest · Maintenance 3/20
Static review · not runListed 2026-09-10
Read the FMRS scoring method →Runtime：Python 3.12+
UNSTRUCTURED_API_KEY
Required key for the Unstructured API, obtained from platform.unstructured.io API keys page.
ANTHROPIC_API_KEY
Needed to run the minimal_client to interact with the server; from the Anthropic console.
AWS_SECRET
AWS secret access key required to create S3 connectors.
WEAVIATE_CLOUD_API_KEY
Required to create a Weaviate vector DB connector; from Weaviate Cloud.
FIRECRAWL_API_KEY
Required for the Firecrawl tools; sign up at firecrawl.dev to get one.
ASTRA_DB_APPLICATION_TOKEN
Auth token required to create an AstraDB connector; from DataStax Astra.
AZURE_CONNECTION_STRING
Option 1 for creating an Azure connector: the Azure storage connection string.
AZURE_ACCOUNT_KEY
Azure storage account key for connector option 2.
AZURE_SAS_TOKEN
Azure SAS token for connector option 3.
NEO4J_PASSWORD
Database password required to create a Neo4j connector.
MONGO_DB_CONNECTION_STRING
Connection string required to create a MongoDB connector.
GOOGLEDRIVE_SERVICE_ACCOUNT_KEY
Base64-encoded string of the Google service account JSON key for Google Drive source connectors.
DATABRICKS_CLIENT_SECRET
Client secret required to create Databricks connectors.
ONEDRIVE_CLIENT_CRED
Client credential required to create a OneDrive connector.
PINECONE_API_KEY
Required to create a Pinecone vector DB connector; from the Pinecone console.
SALESFORCE_PRIVATE_KEY
Private key required to create a Salesforce source connector.
SHAREPOINT_CLIENT_CRED
Client credential required to create a SharePoint source connector.
AWS_KEY
AWS access key ID required to create S3 connectors.
ASTRA_DB_API_ENDPOINT
API endpoint required to create an AstraDB connector.
AZURE_ACCOUNT_NAME
Azure storage account name for connector options 2 and 3.
DATABRICKS_CLIENT_ID
Client ID required to create Databricks connectors.
ONEDRIVE_CLIENT_ID
App client ID required to create a OneDrive connector.
ONEDRIVE_TENANT_ID
Tenant ID required to create a OneDrive connector.
SALESFORCE_CONSUMER_KEY
Consumer key required to create a Salesforce source connector.
SHAREPOINT_CLIENT_ID
Client ID required to create a SharePoint source connector.
SHAREPOINT_TENANT_ID
Tenant ID required to create a SharePoint source connector.
LOG_LEVEL
Sets the minimal_client logging level, e.g. ERROR to suppress debug output.
CONFIRM_TOOL_USE
Set to true so the minimal_client confirms execution before each tool call.
DEBUG_API_REQUESTS
Set to true so the server outputs request parameters for debugging.
Prerequisites: Python 3.12+, uv for environment management, and an API key from Unstructured. Using uvx is recommended (no additional installation required). Configure mcpServers.UNS_MCP in claude_desktop_config.json (located in ~/Library/Application Support/Claude/) with command uvx, args ["uns_mcp"], and env UNSTRUCTURED_API_KEY. Alternatively use the Python package with command python and args ["-m", "uns_mcp"]. From source: clone the repository, run uv sync, create a .env file in the root directory with UNSTRUCTURED_API_KEY (see .env.template). For SSE, run uv run python uns_mcp/server.py --host 127.0.0.1 --port 8080 (or make sse-server) and test with the local client; Claude Desktop does not support SSE. For stdio, point the Claude Desktop config at your local uv executable and run server.py.
{
"mcpServers": {
"UNS_MCP": {
"command": "uvx",
"args": ["uns_mcp"],
"env": {
"UNSTRUCTURED_API_KEY": "<your-key>"
}
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"UNS_MCP": {
"command": "uvx",
"args": [
"uns_mcp"
],
"env": {
"UNSTRUCTURED_API_KEY": "<your-key>"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add UNS_MCP -e 'UNSTRUCTURED_API_KEY=<your-key>' -- uvx uns_mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
After starting the server in Claude Desktop, check the tool list for tools like list_sources and list_workflows; then ask "list my sources" — a returned connector list confirms the connection works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
An MCP server implementation for interacting with the Unstructured API, providing tools to manage sources, destinations, and workflows. It includes tools to list, create, update, and delete connectors, create and run workflows, inspect and cancel jobs, plus Firecrawl-based web crawling features. Note that this server is not actively maintained and is kept for reference; for parsing and transforming files into structured output (markdown, JSON, HTML, or plain text), the README recommends the Unstructured Transform MCP server instead. To use the tools that create, update, or delete a connector, the credentials for that specific connector must be defined in the .env file.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision fa52862ec7fc Data synced 2026-10-19 Read the FMRS scoring method