Model Context Protocol security

mcpwn

X-ray and tamper the traffic between an AI agent and its MCP servers. An intercepting man-in-the-middle proxy for the Model Context Protocol - watch every JSON-RPC message, and rewrite the tool results the server sends back to the agent. Burp Suite, but for AI agents.

Quickstart → GitHub

⚠ Authorized testing only - use it on agents and servers you own or are explicitly authorized to assess.

mcpwn scans a vulnerable MCP server: it enumerates the tools, fuzzes them, and reports findings by severity with CWE mappings
scan a server → fuzz every tool → findings ranked by severity, with CWEs

One tool, six jobs

30-second quickstart

# Passive X-ray — watch all traffic, change nothing
mcpwn -v -- npx -y @modelcontextprotocol/server-filesystem /tmp
# Apply JSON tamper rules to messages in flight
mcpwn -r attack.json -- node ./my-server.js
# Self-driving scan — fail CI on findings at/above a severity
mcpwn scan --fuzz --findings-out ./out --fail-on high -- node ./my-server.js
# Route your MCP client's servers through mcpwn (backed up, reversible)
mcpwn wrap --client claude-desktop

Threat coverage

Fifteen MCP attack classes, each with a CWE, a detector/template/dvmcp server, and a fix.