mcp-nlp

What is mcp-nlp?

MCP-NLP is a FastMCP application built with the FastMCP v2 framework that provides NLP capabilities, specifically text distance metrics via the textdistance module, using the Model Context Protocol (MCP).

How to use mcp-nlp?

Clone the repository, install dependencies with uv sync, then run locally using uvicorn app.main:http_app --reload or build and run a Docker container with docker build -t mcp-nlp . followed by docker run --rm -p 8000:8000 mcp-nlp. The MCP server endpoint is accessible at http://127.0.0.1:8000/mcp/ using the streamable-http transport.

Key features of mcp-nlp

• Built on the FastMCP v2 framework for Pythonic MCP servers
• Provides NLP text distance calculations via textdistance
• Supports local and Docker deployment
• Uses streamable-http transport
• Requires Python 3.12, Docker, and uv

Use cases of mcp-nlp

• Compute text similarity or distance between strings
• Add NLP functionality to LLM context management pipelines
• Deploy a lightweight MCP server for text analysis tasks

FAQ from mcp-nlp

What is MCP-NLP?

MCP-NLP is a FastMCP application that provides NLP capabilities, including text distance metrics, using the Model Context Protocol.

What are the prerequisites?

Python 3.12, Docker, and uv are required.

How do I run the MCP server locally?

Create a .env file, then run uvicorn app.main:http_app --reload and access the endpoint at http://127.0.0.1:8000/mcp/.

How do I run it using Docker?

Build the image with docker build -t mcp-nlp . and run the container with docker run --rm -p 8000:8000 mcp-nlp.