Question 1

What is an MCP Server?

Accepted Answer

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. An MCP Server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

Question 2

What is the Unstructured API MCP Server?

Accepted Answer

It's a specific MCP server implementation designed for interacting with the Unstructured API. It provides tools to list sources, destinations, workflows, and manage data processing jobs.

Question 3

What tools are available in the Unstructured API MCP Server?

Accepted Answer

The server provides tools for listing, getting info, creating, updating, and deleting sources, destinations, and workflows. It also allows you to list, get info, and cancel jobs.

Question 4

What data sources and destinations does the MCP Server support?

Accepted Answer

Currently, the server supports S3, Azure, Google Drive, OneDrive, Salesforce, and Sharepoint as sources. Destinations include S3, Weaviate, Pinecone, AstraDB, MongoDB, Neo4j, Databricks Volumes, and Databricks Volumes Delta Table. See full list of supported sources [here](https://docs.unstructured.io/api-reference/workflow/sources/overview) and destinations [here](https://docs.unstructured.io/api-reference/workflow/destinations/overview)

Question 5

What is Firecrawl and how does it integrate with the MCP Server?

Accepted Answer

Firecrawl is a web crawling API that allows you to retrieve HTML content or generate LLM-optimized text from websites. The MCP Server provides tools to invoke Firecrawl crawls and check their status.

Question 6

What credentials are required to use the connector tools?

Accepted Answer

Each connector requires specific credentials defined in your `.env` file. Refer to the documentation for a list of required credentials for each connector.

Question 7

How do I install and configure the Unstructured API MCP Server?

Accepted Answer

The installation process involves using Python 3.12+, installing the `uns_mcp` package, configuring Claude Desktop (if using), and setting the necessary environment variables, including your Unstructured API key.

Question 8

What is UBOS, and how does the MCP Server fit into the UBOS platform?

Accepted Answer

UBOS is a full-stack AI Agent Development Platform. The MCP Server integrates into UBOS by providing a way to connect AI Agents with external data sources and tools, enabling more complex and data-driven AI applications.

Question 9

Can I use a subset of tools with my client?

Accepted Answer

Yes, you can. However, if you're using `update_workflow`, it must be loaded in the context with `create_workflow` because it provides details on how to create and configure custom nodes.

Question 10

Where can I find the changelog for updates and new features?

Accepted Answer

All new features, fixes, and enhancements are documented in the `CHANGELOG.md` file.

Unstructured API Server

Resources

Project Details

Recomended MCP Servers

Featured Templates

Python Bug Fixer

AI Chat Bot: Text, Voice, and Video Magic

Talk with Claude 3

Image Generation with Stable Diffusion

Image to text with Claude 3

Customer Relationship Management (CRM)

Start your free trial