Skip to main content
Glama

ConceptNet MCP Server

by infinitnet
GitHub
Python
GPL 3.0
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

ConceptNet MCP Server

A Model Context Protocol (MCP) server that provides seamless access to the ConceptNet knowledge graph through FastMCP framework.

CI Release Python 3.10+ License: GPL-3.0

Overview

ConceptNet MCP provides AI assistants and applications with structured access to ConceptNet's semantic knowledge through four powerful MCP tools:

  • Concept Lookup: Get detailed information about specific concepts

  • Concept Query: Search and filter concepts with advanced criteria

  • Related Concepts: Find concepts connected through semantic relationships

  • Concept Relatedness: Calculate semantic similarity between concepts

Features

  • 🚀 FastMCP Integration: Built on the modern FastMCP framework for optimal performance

  • 🔍 Comprehensive Search: Advanced querying with language filtering and pagination

  • 🌐 Multi-language Support: Access ConceptNet's multilingual knowledge base

  • 📊 Semantic Analysis: Calculate relatedness scores between concepts

  • 🔄 Async Operations: Full async/await support for non-blocking operations

  • 📝 Type Safety: Complete Pydantic v2 type validation and IDE support

  • 🧪 Production Ready: Error handling, logging, and testing

  • ⚡ Optimized Output Formats: Choose between minimal (~96% smaller) or comprehensive responses

Output Formats

ConceptNet MCP Server supports two output formats for all tools to optimize performance and reduce token usage:

Minimal Format (Default - Recommended)

  • Size: ~96% smaller than verbose format

  • Optimized: Designed specifically for LLM consumption

  • Content: Essential data only - concepts, relationships, similarity scores

  • Performance: Faster processing and reduced API costs

  • Usage: Perfect for most AI applications and chat interfaces

Verbose Format

  • Size: Full ConceptNet response data

  • Content: Complete metadata, statistics, analysis, and original API responses

  • Usage: Detailed analysis, debugging, or when full context is needed

  • Backward Compatibility: Maintains compatibility with existing integrations

Setting the Format

All tools accept a verbose parameter:

{ "name": "concept_lookup", "arguments": { "term": "artificial intelligence", "verbose": false // Default: minimal format } }
{ "name": "related_concepts", "arguments": { "term": "machine learning", "verbose": true // Full detailed format } }

Examples of size difference:

  • Minimal: {"concept": "dog", "relationships": {"IsA": ["animal", "mammal"]}}

  • Verbose: Full ConceptNet response with complete metadata, statistics, timestamps, etc.

Quick Start

Installation

# Clone the repository git clone https://github.com/infinitnet/conceptnet-mcp.git cd conceptnet-mcp # Install in development mode pip install -e .

Running the MCP Server

The server supports both stdio (for desktop MCP clients) and HTTP (for web clients) transport modes:

Stdio Transport (Default - for desktop MCP clients)

# Start with stdio transport (default) conceptnet-mcp # Or explicitly specify stdio conceptnet-mcp-stdio # Or use Python module python -m conceptnet_mcp.server

HTTP Transport (for web clients)

# Start HTTP server on localhost:3001 conceptnet-mcp-http # Or with custom host/port python -c "from conceptnet_mcp.server import run_http_server; run_http_server('0.0.0.0', 8080)"

Development Modes

# Development mode with debug logging conceptnet-mcp-dev # Production mode with optimized logging conceptnet-mcp-prod

MCP Client Integration

For Desktop MCP Clients (stdio transport)

Add to your MCP client configuration:

{ "mcpServers": { "conceptnet": { "command": "python", "args": ["-m", "conceptnet_mcp.server"] } } }

For Web Applications (HTTP transport)

Add to your MCP client configuration:

{ "mcpServers": { "conceptnet": { "command": "python", "args": ["-m", "conceptnet_mcp.server", "--transport", "http", "--port", "3001"] } } }

Or start the HTTP server manually and connect to:

http://localhost:3001
// Example web client connection const client = new MCPClient('http://localhost:3001'); await client.connect();

☁️ Cloudflare Workers Deployment

Deploy ConceptNet MCP Server to Cloudflare's global edge network for worldwide access and automatic scaling using a FastAPI-based implementation optimized for Python Workers.

Deploy to Cloudflare Workers

Architecture

The Cloudflare Workers deployment uses a completely different architecture from the standard FastMCP server:

  • FastAPI Framework: Manual MCP protocol implementation using FastAPI for HTTP routing

  • Standard Workers Pattern: Uses fetch(request, env, ctx) handler (no Durable Objects)

  • Native HTTP Client: Custom CloudflareHTTPClient using Workers' native fetch() API

  • Manual MCP Protocol: JSON-RPC 2.0 MCP messages handled directly without FastMCP framework

Benefits

  • 🌍 Global Edge Network: Low-latency access worldwide via Cloudflare's CDN

  • 🚀 Auto-scaling: Serverless scaling based on demand with zero cold starts

  • 🔄 Dual Transport Support: Both SSE and Streamable HTTP endpoints for maximum compatibility

  • 🤖 Remote MCP Access: Enable AI agents to access ConceptNet from anywhere

  • 💰 Cost-effective: Pay only for actual usage with generous free tier

Quick Deploy

# Clone and navigate to Workers directory git clone https://github.com/infinitnet/conceptnet-mcp.git cd conceptnet-mcp/cloudflare-workers # Install Wrangler CLI npm install -g wrangler # Authenticate and deploy wrangler login wrangler deploy

Usage After Deployment

Your ConceptNet MCP Server will be available at:

# Streamable HTTP Transport (recommended for MCP clients) https://your-worker.your-domain.workers.dev/mcp # SSE Transport (legacy support) https://your-worker.your-domain.workers.dev/sse # Tools listing endpoint https://your-worker.your-domain.workers.dev/tools

Example remote client connection (direct HTTP):

import httpx import json # Connect to your deployed Workers instance async with httpx.AsyncClient() as client: response = await client.post( "https://your-worker.your-domain.workers.dev/mcp", json={ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "concept_lookup", "arguments": {"term": "artificial intelligence"} } } ) result = response.json() print(result["result"])

For detailed deployment instructions, configuration options, and troubleshooting, see the Cloudflare Workers Documentation.

Available Tools

1. Concept Lookup

Get detailed information about a specific concept. Returns all relationships and properties.

{ "name": "concept_lookup", "arguments": { "term": "artificial intelligence", "language": "en", "limit_results": false, "target_language": null, "verbose": false } }

Parameters:

  • term (required): The concept to look up

  • language (default: "en"): Language code for the concept

  • limit_results (default: false): Limit to first 20 results for quick queries

  • target_language (optional): Filter results to specific target language

  • verbose (default: false): Return detailed format vs minimal format

2. Concept Query

Advanced querying with sophisticated multi-parameter filtering.

{ "name": "concept_query", "arguments": { "start": "car", "rel": "IsA", "language": "en", "limit_results": false, "verbose": false } }

Parameters:

  • start (optional): Start concept of relationships

  • end (optional): End concept of relationships

  • rel (optional): Relation type (e.g., "IsA", "PartOf")

  • node (optional): Concept that must be start or end of edges

  • other (optional): Used with 'node' parameter

  • sources (optional): Filter by data source

  • language (default: "en"): Language filter

  • limit_results (default: false): Limit to 20 results for quick queries

  • verbose (default: false): Return detailed format vs minimal format

3. Related Concepts

Find concepts semantically similar to a given concept using ConceptNet's embeddings.

{ "name": "related_concepts", "arguments": { "term": "machine learning", "language": "en", "filter_language": null, "limit": 100, "verbose": false } }

Parameters:

  • term (required): The concept to find related concepts for

  • language (default: "en"): Language code for input term

  • filter_language (optional): Filter results to this language only

  • limit (default: 100, max: 100): Maximum number of related concepts

  • verbose (default: false): Return detailed format vs minimal format

4. Concept Relatedness

Calculate precise semantic relatedness score between two concepts.

{ "name": "concept_relatedness", "arguments": { "concept1": "artificial intelligence", "concept2": "machine learning", "language1": "en", "language2": "en", "verbose": false } }

Parameters:

  • concept1 (required): First concept for comparison

  • concept2 (required): Second concept for comparison

  • language1 (default: "en"): Language for first concept

  • language2 (default: "en"): Language for second concept

  • verbose (default: false): Return detailed format vs minimal format

Configuration

The server can be configured through environment variables:

# ConceptNet API settings CONCEPTNET_API_BASE_URL=https://api.conceptnet.io CONCEPTNET_API_VERSION=5.7 # Server settings MCP_SERVER_HOST=localhost MCP_SERVER_PORT=3000 LOG_LEVEL=INFO # Rate limiting CONCEPTNET_RATE_LIMIT=100 CONCEPTNET_RATE_PERIOD=60

Development

Setup

# Clone the repository git clone https://github.com/infinitnet/conceptnet-mcp.git cd conceptnet-mcp # Install in development mode pip install -e .[dev] # Install pre-commit hooks pre-commit install

API Reference

Core Models

  • Concept: Represents a ConceptNet concept with URI, label, and language

  • Edge: Represents relationships between concepts with relation types

  • Query: Structured query parameters for concept searches

  • Response: Standardized response format with pagination support

Client Components

  • ConceptNetClient: Async HTTP client for ConceptNet API

  • PaginationHandler: Automatic pagination for large result sets

  • ResponseProcessor: Data processing and normalization

Utilities

  • Text Processing: Normalize text (underscores to spaces)

  • Logging: Structured logging with configurable levels

  • Error Handling: Comprehensive exception hierarchy

Architecture

conceptnet_mcp/ ├── client/ # ConceptNet API client │ ├── conceptnet_client.py │ ├── pagination.py │ └── processor.py ├── models/ # Pydantic data models │ ├── concept.py │ ├── edge.py │ ├── query.py │ └── response.py ├── tools/ # MCP tool implementations │ ├── concept_lookup.py │ ├── concept_query.py │ ├── related_concepts.py │ └── concept_relatedness.py ├── utils/ # Utility modules │ ├── exceptions.py │ ├── logging.py │ └── text_utils.py └── server.py # FastMCP server entry point

Contributing

  1. Fork the repository: https://github.com/infinitnet/conceptnet-mcp

  2. Create a feature branch: git checkout -b feature-name

  3. Make your changes and add tests

  4. Run the test suite: python run_tests.py

  5. Submit a pull request

Guidelines

  • Follow PEP 8 style guidelines

  • Add type hints for all functions

  • Include docstrings for public APIs

  • Write tests for new functionality

  • Update documentation as needed

License

This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.

Acknowledgments

Support

Built with ❤️ for the AI and semantic web community.

Deploy Server
-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Tools

Provides seamless access to the ConceptNet semantic knowledge graph, enabling concept lookup, search, relationship discovery, and semantic similarity calculations across multiple languages.

  1. Overview
    1. Features
      1. Output Formats
        1. Minimal Format (Default - Recommended)
        2. Verbose Format
        3. Setting the Format
      2. Quick Start
        1. Installation
        2. Running the MCP Server
        3. MCP Client Integration
      3. ☁️ Cloudflare Workers Deployment
        1. Architecture
        2. Benefits
        3. Quick Deploy
        4. Usage After Deployment
      4. Available Tools
        1. 1. Concept Lookup
        2. 2. Concept Query
        3. 3. Related Concepts
        4. 4. Concept Relatedness
      5. Configuration
        1. Development
          1. Setup
        2. API Reference
          1. Core Models
          2. Client Components
          3. Utilities
        3. Architecture
          1. Contributing
            1. Guidelines
          2. License
            1. Acknowledgments
              1. Support

                Related MCP Servers

                • Notion MCP Server

                  v-3
                  -
                  security
                  A
                  license
                  -
                  quality
                  Enables Language Models to interact with Notion workspaces through standardized tools for searching, reading, creating, and updating pages and databases.
                  Last updated -
                  116
                  MIT License
                  • Apple

                • Knowledge Base MCP Server

                  jeanibarz
                  A
                  security
                  A
                  license
                  A
                  quality
                  Provides tools for listing and retrieving content from different knowledge bases using semantic search capabilities.
                  Last updated -
                  2
                  26
                  The Unlicense
                  • Linux
                  • Apple

                • Memory MCP Server

                  evangstav
                  -
                  security
                  A
                  license
                  -
                  quality
                  Provides knowledge graph functionality for managing entities, relations, and observations in memory with strict validation rules to maintain data consistency.
                  Last updated -
                  16
                  MIT License

                • Project MCP Server

                  tejpalvirk
                  A
                  security
                  F
                  license
                  A
                  quality
                  Provides tools for managing project knowledge graphs, enabling structured representation of projects, tasks, milestones, resources, and team members.
                  Last updated -
                  6
                  10
                  • Apple
                  • Linux

                View all related MCP servers

                New MCP Servers

                MCP directory API

                We provide all the information about MCP servers via our MCP API.

                curl -X GET 'https://glama.ai/api/mcp/v1/servers/infinitnet/conceptnet-mcp'

                If you have feedback or need assistance with the MCP directory API, please join our Discord server