UNS-MCP
The Unstructured API MCP Server is designed to manage and interact with multiple data connectors and workflows using the Unstructured API. It supports various source and destination platforms, including AWS S3, Azure, and Google Drive, with tools for creating, updating, and deleting connectors and workflows.
What is the Unstructured API MCP Server?
It is a server implementation for interacting with the Unstructured API, providing tools for managing sources, destinations, and workflows.
What connectors are supported by the UNS-MCP server?
The server supports connectors like S3, Azure, Google Drive, OneDrive, Salesforce, and various databases such as Weaviate, Pinecone, AstraDB, MongoDB, Neo4j, and Databricks.
How do I configure the server for use with Claude Desktop?
You can configure Claude Desktop by adding the server details to the claude_desktop_config.json file, specifying the command and environment variables.
What is Firecrawl and how is it integrated?
Firecrawl is a web crawling API integrated into the MCP server for HTML content retrieval and LLM-optimized text generation.
How can I debug the MCP server?
You can use the MCP Inspector tool provided by Anthropic to debug and test your MCP server, allowing you to add environment variables and test tool capabilities.