cwe-search_mcp
Enables querying MITRE's Common Weakness Enumeration database for vulnerability information, supporting CWE lookup, search, taxonomy navigation, and relationship mapping through MCP.
README
CWE Search MCP
A Python-based interface to MITRE's Common Weakness Enumeration (CWE) database via the official API, enabling seamless vulnerability research and integration with MCP-compatible systems.
Overview
The CWE Search MCP provides a robust Python implementation for interacting with MITRE's Common Weakness Enumeration (CWE) database through its official API. Designed for security researchers, developers, and vulnerability analysts, this mcp enables efficient querying of vulnerability information and integrates seamlessly with MCP-compatible systems using stdio transport.
This solution solves the problem of fragmented vulnerability research by providing a unified interface to:
- Retrieve detailed CWE information programmatically
- Explore vulnerability relationships and hierarchies
- Integrate CWE data into security tooling and workflows
- Automate vulnerability analysis and reporting
Key Features
- Comprehensive Vulnerability Lookup: Retrieve detailed information by CWE ID
- Intelligent Search: Find vulnerabilities by keyword across descriptions
- Taxonomy Navigation: Explore CWE categories and views
- Relationship Mapping:
- Parent/child vulnerability relationships
- Full ancestor/descendant hierarchies
- View-filtered relationship analysis
- Automatic Normalization: Handles CWE IDs with or without "CWE-" prefix
- Zero Configuration: No authentication required for MITRE's public API
- MCP Integration: Ready for stdio transport with MCP-compatible systems
- Batch Processing: Retrieve multiple vulnerabilities in single requests
Implemented API Endpoints
The mcp implements the following MITRE CWE API endpoints:
| Endpoint | Description |
|---|---|
/cwe/version |
Get CWE content version information |
/cwe/{id} |
Retrieve metadata for specified CWE ID(s) |
/weakness/{id(s)} |
Get weaknesses by ID(s) or all weaknesses |
/cwe/category/{id(s)} |
Retrieve categories by ID(s) or all categories |
/cwe/view/{id(s)} |
Get views by ID(s) or all views |
/cwe/{id}/parents |
Get parents of a weakness (view-filtered) |
/cwe/{id}/children |
Get children of a weakness (view-filtered) |
/cwe/{id}/ancestors |
Get ancestors of a weakness (view-filtered) |
/cwe/{id}/descendants |
Get descendants of a weakness (view-filtered) |
Getting Started
Prerequisites
- Python 3.10+
- uv package manager
Installation
-
Clone the repository:
git clone https://github.com/Bilel-Eljaamii/cwe-search_mcp.git cd cwe-search_mcp -
Install dependencies:
pip install requests fast-mcp
Usage Guide
Standalone Execution
Run the mcp as a standalone module:
DANGEROUSLY_OMIT_AUTH=true mcp dev main.py
Output:
[06/28/25 12:46:09] INFO Starting cwe-search_mcp
Starting MCP inspector...
ā Proxy server listening on 127.0.0.1:6277
ā WARNING: Authentication is disabled. This is not recommended.
New STDIO connection request
STDIO transport: command=/usr/bin/uv, args=run,--with,mcp,mcp,run,main.py
Created server transport
Created client transport
š MCP Inspec

MCP Client Integration
To integrate the CWE Search Service with your MCP client:
-
Locate Configuration: Open your MCP client configuration file
-
Update Path: Set CWE_SEARCH_SERVICE_PATH to the absolute path of your local installation directory
-
Add to your mcp client configuration file, modify the 3.
"CWE_SEARCH_SERVICE_PATH"as you self dir.
"cwe-search_mcp": {
"autoApprove": [],
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"CWE_SEARCH_SERVICE_PATH",
"run",
"main.py"
]
}
AnythingLLM

Cline / VSCode

Key Notes
- Authentication: No credentials required - MITRE's CWE API is publicly accessible
- Input Normalization: MCP automatically handles CWE ID formats:
79ā Normalized to79CWE-79ā Normalized to79cwe79ā Normalized to79
- Batch Processing: Comma-separated IDs supported for most endpoints
allKeyword: Retrieve all items for weakness, category, and view endpoints
Dependencies
- requests - HTTP library for API communication
- fastmcp - The fast, Pythonic way to build MCP servers and clients.
# Using uv (recommended)
uv init
uv venv
source ./venv/bin/activate
uv pip install "mcp[cli]" "requests"
Contributing
We welcome contributions! Please follow these steps:
- Fork the repository
- Create your feature branch (
git checkout -b feature/your-feature) - Commit your changes (
git commit -am 'Add some feature') - Push to the branch (
git push origin feature/your-feature) - Open a pull request
Please ensure your code follows PEP 8 style guidelines and includes appropriate tests.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgements & Resources
- MITRE Corporation for maintaining the Common Weakness Enumeration database
- Official CWE Website
- CWE API Documentation
- CWE List Version 4.14
Empower your vulnerability research with direct access to MITRE's CWE database through this lightweight, integration-ready MCP. Contribute, customize, and enhance your security workflows today!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.