reptor-mcp

reptor-mcp: An MCP Server for Reptor/SysReptor

This project transforms thereptorCLI tool into an MCP (Model-Context-Protocol) server, exposing its powerful pentest reporting and automation features as a programmable service.

It allows other tools, scripts, or AI agents to programmatically interact with SysReptor via the MCP protocol, facilitating integration into automated workflows.

[!WARNING]Alpha Software:The underlyingreptorCLI tool is in alpha. Its API may change, potentially breakingreptor-mcp.

[!CAUTION]No Authentication:This server hasno authentication or authorization. It is designed for local use only.DO NOT EXPOSE IT TO THE INTERNET OR UNTRUSTED NETWORKS.

[!IMPORTANT]Data Sensitivity:If you handle sensitive project data, consider the implications of sending it to LLMs via this server. UseREPTOR_MCP_EXCLUDE_FIELDSto strip sensitive fields before they reach the LLM.

- Dynamic Tool Generation:Automatically creates MCP tools from all availablereptorplugins (nmap, nessus, burp, zap, sslyze, etc.).
- Direct API Tools:Provides structured tools for findings CRUD, schema discovery, and template management using reptor's Python API directly.
- Field Exclusion:Strips sensitive fields from data before returning it to LLM clients (configurable via environment variable).
- Async-Safe:Non-blocking event loop with thread-safe serialized plugin execution.

- Python 3.10+
- uv(recommended) orpip
- A running[SysReptorinstance with an API token

git clone https://github.com/slvnlrt/reptor-mcp.git cd reptor-mcp uv venv && source .venv/bin/activate uv pip install -e .

This installsreptorandfastmcpautomatically from PyPI. No need to clone the reptor repository separately.

If you need to work against a local checkout of reptor (e.g. to test unreleased changes):

uv pip install -e /path/to/reptor-source uv pip install -e .

Alternatively, setREPTOR_MAIN_PATH=/path/to/reptor-sourceat runtime to inject it intosys.path.

The server is configured via environment variables:

fastmcp run mcp_server.py:mcp --transport streamable-http --port 8008

The server will be accessible athttp://localhost:8008/mcp/.

Connect an MCP client using a configuration like this (e.g., inmcp_settings.json):

{ "mcpServers": { "reptor-mcp": { "type": "streamable-http", "url": "http://localhost:8008/mcp/" } } }

These tools use reptor's Python API directly for structured, schema-aware operations:

The server dynamically wraps allreptorCLI plugins as MCP tools:

The exact arguments for each tool can be inspected via a connected MCP client.