CedricG-dev

VulnerabilityMCPServer

Community CedricG-dev
Updated

VulnerabilityMCPServer

Test d'un serveur MCP local sur le protocol HTTP

Prerequisites

A python version 3.9+ should be installed

NPM should be installed (using NodeJS installation)

Set up environment

  1. Clone the Github repo

  2. Unzip vulnerability.zip in data folder

  3. Create a virtual environement linked to the project

python -m venv <PATH_TO_YOU_VENV_FOLDER>\VulnerabilityMCPServer
  1. Start virtual environement
<PATH_TO_YOU_VENV_FOLDER>\Scripts\Activate.ps1

Use other script based on you environment type (activate / activate.bat)

  1. Install python packages
pip install -r requirements.txt
  1. Launch the MCP server
python src/vulnerability-mcp-server.py

The terminal should render:

SERVER START

Test MCP server

Open another terminal and launch the command

npx @modelcontextprotocol/inspector

if a prompt ask you if you want to install the package accept

Now a browser is opened and display MCP inspector

MCP INSPECTOR

Click on Add Servers ans select + Add manually

Set VULN-SERVER as Server ID

Select streamable-httpas Transport

Set URL with http://localhost:8000/mcp and click on Add

A new serevr appears:

MCP INSPECTOR

Toogle on Conction button at the top-right of the server card

Some info should appear on a right side bar.

Click on Tools and select get_vulnerability_data.

TOOL PICTURES

Fille cve_-_id with for example CVE-2025-53770

RESULT

Run OpenCode

Now you can run OpenCode in a third terminal.

opencode

you get

OPENCODE

use the command /mcps to list mcp servers

OPENCODE MCP

Now test the following prompt


get info about vulnerability with id  CVE-2025-53770 and trace if you used a mcp server and a tool in your response

We get the following response with local LLM qwen3.6:latest

RESPONSE QWEN

We get the following response with remote Claude Sonnet 5

RESPONS SONNET

MCP Server ยท Populars

MCP Server ยท New

    drakulavich

    Kesha Voice Kit

    Give your tools a voice โ€” speech to text and back, 25 languages, up to ~19ร— faster than Whisper. On your machine.

    Community drakulavich
    lobu-ai

    Lobu โ€” Open-source backend for AI teammates

    Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.

    Community lobu-ai
    minipuft

    Claude Prompts MCP Server

    Wolfflow: Model Context Protocol (MCP) server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.

    Community minipuft
    docmancer

    Docmancer

    Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. Local-first, MIT.

    Community docmancer
    lineai-intelligence

    codelogic-mcp-server

    An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.