
osv-mcp
MCP Server for Vulnerabilities based on OSV API
3 years
Works with Finder
0
Github Watches
0
Github Forks
0
Github Stars
OSV MCP Server
This project provides an MCP (Model Context Protocol) server for integrating OSV (Open Source Vulnerabilities) data and tools with AI assistants or large language models (LLMs). The server is implemented in Python and exposes tools and resources that can be used by LLMs to enhance their workflow and capabilities. Here is a screenshot of Claude Desktop using the OSV MCP Server.
Features
- Exposes OSV-related data via the MCP protocol
- Easily connectable to AI assistants or LLMs that support MCP
- Simple Python-based setup
Prerequisites
- Python 3.8+ installed on your system
- uv (Python package manager, installation instructions)
Setup Instructions
1. Clone the Repository
Clone this repository to your local machine:
git clone https://github.com/your-org/osv-mcp.git
cd osv-mcp
2. Create a Virtual Environment (Recommended)
It is recommended to use a virtual environment to avoid dependency conflicts:
curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
3. Install Dependencies
Install the required Python packages using uv:
uv sync
4. Start the MCP Server
Run the server using:
uv run vulns.py
Using MCP Servers with AI Assistants and LLMs
MCP servers expose tools and resources over a local or network-accessible API. AI assistants and LLMs that support the Model Context Protocol can connect to one or more MCP servers to extend their capabilities. Once connected, the assistant can invoke the query_vulnerabilities tool.
Consult your AI assistant or LLM's documentation for specific instructions on adding or configuring MCP servers.
Using OSV MCP Server with Claude Desktop
Add the OSV MCP server in claude_desktop_config.json
file.
On Mac or Linux, edit: ~/Library/Application\ Support/Claude/claude_desktop_config.json
.
On Windows, edit: env:AppData\Claude\claude_desktop_config.json
.
Add the OSV MCP server to the config as below.
{
"mcpServers": {
"vulns": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/osv-mcp",
"run",
"vulns.py"
]
}
}
}
Development
- Source code is in
vulns.py
. - Project dependencies are managed via
pyproject.toml
.
License
MIT License (or specify your license here)
For further questions or support, please open an issue or contact the maintainers.
相关推荐
🧑🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.
🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.
⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
😎简单易用、🧩丰富生态 - 大模型原生即时通信机器人平台 | 适配 QQ / 微信(企业微信、个人微信)/ 飞书 / 钉钉 / Discord / Telegram / Slack 等平台 | 支持 ChatGPT、DeepSeek、Dify、Claude、Gemini、xAI、PPIO、Ollama、LM Studio、阿里云百炼、火山方舟、SiliconFlow、Qwen、Moonshot、ChatGLM、SillyTraven、MCP 等 LLM 的机器人 / Agent | LLM-based instant messaging bots platform, supports Discord, Telegram, WeChat, Lark, DingTalk, QQ, Slack
Reviews

user_SJJCKnIb
As an avid user of osv-mcp, I am thoroughly impressed by its capabilities and user-friendly interface. This tool, developed by ptelang, has significantly streamlined my workflow and enhanced productivity. Its seamless integration and robust features make it a must-have for any professional. Highly recommended!

user_BPeqYEvs
As a dedicated user of osv-mcp, I can say this product, created by ptelang, is exceptional. The user-friendly interface and seamless integration make it a must-have for anyone looking to enhance their MCP application experience. Highly recommended!