trackmcp
Back to directory
invariantlabs-ai

mcp-injection-experiments

View on GitHub

Code snippets to reproduce MCP tool poisoning attacks. Python-based implementation.

183 stars PythonDeveloper Kits Updated Oct 14, 2025

No README could be loaded. View the project on GitHub for full documentation.

Frequently asked questions

What is mcp-injection-experiments?

mcp-injection-experiments is Code snippets to reproduce MCP tool poisoning attacks. Python-based implementation.

How do I install mcp-injection-experiments?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is mcp-injection-experiments open source?

Yes — it is hosted on GitHub at https://github.com/invariantlabs-ai/mcp-injection-experiments and has 183 stars.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP