Contact

ConceptNet MCP Server

The ConceptNet MCP Server is a Model Context Protocol server that gives AI assistants and applications structured access to the ConceptNet knowledge graph. It is built with the FastMCP framework.

What it does

Four MCP tools cover the semantic knowledge:

  • Concept lookup: detailed information about a specific concept.
  • Concept query: search and filter concepts with advanced criteria.
  • Related concepts: find concepts connected through semantic relationships.
  • Concept relatedness: calculate the semantic similarity between two concepts.

Features

  • Language filtering and pagination, with access to ConceptNet's multilingual knowledge base.
  • Two output formats: the minimal default is designed for LLMs and is about 96% smaller than the verbose format, which returns the full ConceptNet data.
  • Stdio transport for desktop MCP clients and HTTP transport for web clients.
  • Optional deployment on Cloudflare Workers.

Installation

You need Python 3.10 or newer. Clone the repository, install it and start the server:

git clone https://github.com/infinitnet/conceptnet-mcp.git
cd conceptnet-mcp
pip install -e .
conceptnet-mcp

The README shows the MCP client configuration and the Cloudflare Workers deployment.

Links

Get in touch

Contact Infinitnet