VulnMCP
An MCP server for vulnerability management that provides tools for automated severity and CWE classification using NLP models. It enables AI agents to query the Vulnerability Lookup API for detailed CVE information and search for security vulnerabilities across various sources.
README
VulnMCP
VulnMCP is an MCP server built with FastMCP that provides AI clients, chat agents, and other automated systems with tools for vulnerability management. It offers modular "skills" that can be easily extended or integrated, enabling intelligent analysis and automated insights on software vulnerabilities.
Features
- Vulnerability Severity Classification -- Automatically assess the criticality of vulnerabilities using CIRCL's fine-tuned NLP models: CIRCL/vulnerability-severity-classification-roberta-base (English) and CIRCL/vulnerability-severity-classification-chinese-macbert-base (Chinese).
- CWE Classification -- Predict CWE categories from vulnerability descriptions using CIRCL/cwe-parent-vulnerability-classification-roberta-base.
- Vulnerability Lookup -- Query the Vulnerability Lookup API to get detailed information about specific CVEs or search vulnerabilities by source, CWE, product, or date.
- Modular Architecture -- Easily add new skills or tools to expand the functionality of the MCP server.
Installation
Requires Python 3.10+ and Poetry v2+.
git clone https://github.com/vulnerability-lookup/VulnMCP.git
cd VulnMCP
poetry install
Running the MCP server
stdio (default)
The default transport, used by most MCP clients (Claude Code, Claude Desktop, etc.):
poetry run vulnmcp
HTTP transport
For network access or multiple concurrent clients:
poetry run fastmcp run vulnmcp/server.py --transport http --host 127.0.0.1 --port 9000
Available tools
| Tool | Description |
|---|---|
classify_severity |
Classify vulnerability severity (low/medium/high/critical) from a text description. Supports English and Chinese with auto-detection. |
classify_cwe |
Predict CWE categories from a vulnerability description. Returns top-5 predictions with parent CWE mapping. |
get_recent_vulnerabilities_by_cwe |
Fetch the 3 most recent CVEs for a given CWE ID. |
get_vulnerability |
Look up a specific vulnerability by ID (e.g. CVE-2025-14847) with optional comments, sightings, bundles, and linked vulnerabilities. |
search_vulnerabilities |
Search vulnerabilities with filters: source, CWE, product, date range, pagination. |
List all tools:
poetry run fastmcp list vulnmcp/server.py
Testing tools from the command line
Use fastmcp call to invoke any tool directly:
# Look up a specific CVE
poetry run fastmcp call vulnmcp/server.py get_vulnerability vulnerability_id=CVE-2025-14847
# Search for recent SQL injection vulnerabilities
poetry run fastmcp call vulnmcp/server.py search_vulnerabilities cwe=CWE-89 per_page=5
# Classify severity from a description
poetry run fastmcp call vulnmcp/server.py classify_severity \
description="A remote code execution vulnerability allows an attacker to execute arbitrary code via a crafted JNDI lookup."
# Classify CWE from a description
poetry run fastmcp call vulnmcp/server.py classify_cwe \
description="Fix buffer overflow in authentication handler"
Connecting to Claude Code
Register VulnMCP as an MCP server in Claude Code with:
claude mcp add vulnmcp -- poetry --directory /path/to/VulnMCP run vulnmcp
Or with fastmcp install:
poetry run fastmcp install claude-code vulnmcp/server.py --name VulnMCP
Once registered, the tools are available to Claude Code. You can verify with:
claude mcp list
Configuration
| Environment variable | Description | Default |
|---|---|---|
VULNMCP_LOOKUP_URL |
Base URL for the Vulnerability Lookup API | https://vulnerability.circl.lu |
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。