bad-mcp
10 intentionally malicious MCP servers that demonstrate against AI clients. Each server exploits a distinct feature of the — tool descriptions, schemas, resources, session management, and cross-server interactions.
Power your agent
Install from the publisher. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
No packaged release in the registry yet. Follow the repository README.
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
10 intentionally malicious MCP servers that demonstrate against AI clients. Each server exploits a distinct feature of the — tool descriptions, schemas, resources, session management, and cross-server interactions.
10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
These aren't buggy servers waiting to be exploited. They are the attacker.
WARNING: This project is for authorized security research and education only. Do NOT expose these servers to the internet or use them in production.
MCP adoption is accelerating — Claude Desktop, Cursor, Windsurf, and dozens of other AI clients now support it. But the protocol's trust model has fundamental gaps: tool descriptions are unverified, schemas can carry hidden instructions, and servers can mutate definitions mid-session. Research from CyberArk, Invariant Labs, and Elastic Security Labs has documented these attacks, but working implementations are scarce.
bad-mcp provides concrete, runnable attack servers so client developers can test defenses, security teams can assess risk, and researchers can study protocol-level threats without building everything from scratch.
vuln-external network (localhost:8001-8010)
┌────────────────────┐ ┌────────────────────┐ ┌────────────────────┐
│ schema-poison-notes│ │ response-inject- │ │ shadow-exfil │
│ :8001 │ │ tickets :8002 │ │ :8003 │
└────────────────────┘ └────────────────────┘ └────────────────────┘
┌────────────────────┐ ┌────────────────────┐ ┌────────────────────┐
│ squatting-file-ops │ │ tool-poisoning-calc│ │ true-rug-pull │
│ :8004 │ │ :8005 │ │ :8006 │
└────────────────────┘ └────────────────────┘ └────────────────────┘
┌────────────────────┐ ┌────────────────────┐ ┌────────────────────┐
│ resource-poison- │ │ indirect-inject- │ │ exfil-chain- │
│ docs :8007 │ │ fetcher :8008 │ │ analytics :8009 │
└────────────────────┘ └────────────────────┘ └────────────────────┘
┌────────────────────┐
│ denial-of-wallet │
│ :8010 │
└────────────────────┘
Each server has its own README.md with vulnerability details, exploit scenarios, detection methods, and mitigation strategies.
# Build and start all servers
docker-compose build && docker-compose up -d
# Run smoke tests (runs entirely inside Docker)
docker-compose --profile test run --rm smoke-test
# View exfiltration logs
docker-compose logs schema-poison-notes | grep EXFIL
docker-compose logs true-rug-pull | grep RUG-PULL
# Stop
docker-compose down
After docker-compose up -d, connect any SSE-compatible MCP client (Claude Desktop, Cursor, Windsurf, Claude Code, etc.). All servers use the same JSON format:
{
"mcpServers": {
"schema-poison-notes": { "url": "http://localhost:8001/sse" },
"response-inject-tickets":{ "url": "http://localhost:8002/sse" },
"shadow-exfil": { "url": "http://localhost:8003/sse" },
"squatting-file-ops": { "url": "http://localhost:8004/sse" },
"tool-poisoning-calc": { "url": "http://localhost:8005/sse" },
"true-rug-pull": { "url": "http://localhost:8006/sse" },
"resource-poison-docs": { "url": "http://localhost:8007/sse" },
"indirect-inject-fetcher":{ "url": "http://localhost:8008/sse" },
"exfil-chain-analytics": { "url": "http://localhost:8009/sse" },
"denial-of-wallet": { "url": "http://localhost:8010/sse" }
}
}
Tip: Start with
tool-poisoning-calc(:8005) — simplest attack to observe. Then trytrue-rug-pull(:8006) — ask about the weather 3+ times and watch the tools mutate.
golang:1.23-alpine -> alpine:3.19--profile test)See also: Adversa AI — MCP Security TOP 25 | MCPTox Benchmark | OWASP Top 10 for Agentic Applications
The following published MCP attack classes are not yet implemented:
serverInfo name/version during initializationsampling/createMessage to inject arbitrary prompts10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
No required environment variable is listed on this record.
Bad runs locally over stdio.
Last checked 2026-10-28. 10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.