bad-mcp

10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.

Repo ↗ AI & Machine Learning ai-security llm-security mcp mcp-server model-context-protocol red-team rug-pull security security-research tool-posioning
⚙ Agent Friendliness
N/A
Not evaluated
Can an agent use this?
🔒 Security
N/A
Not evaluated
Is it safe for agents?
⚡ Reliability
N/A
Not evaluated
Does it work consistently?

Scores are editorial opinions as of unknown date.

6470
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered