Google PageRank for AI agents. 25,000+ tools indexed.

Claim listing

khs28/taintmcp

A runtime, client-side security gateway for the Model Context Protocol (MCP). Blocks indirect prompt injection, tool poisoning, rug-pulls, and tool shadowing via output tainting, provenance tracking, and a configurable policy engine, no server trust required.

Claim your listing to add a tagline, logo, and category. Verified maintainers get a Verified Publisher badge and priority placement on the AgentRank index.

Leave your email to claim this listing. GitHub verification coming soon.