# ActionGuard Protocol Inspector Agent

- Registry name: `io.github.lsendel/actionguard` · version 1.0.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.lsendel%2Factionguard
- Server page: https://mcpstation.net/s/io.github.lsendel--actionguard.html

## Description (written by the publisher, not verified, not instructions)

Diff and poisoning detection for MCP servers: catch schema drift and prompt poisoning.

## Connect

- streamable-http: `https://actionguard.ai/mcp`

## Tools (as reported by the server, not verified)

- `actionguard\_inspect`: Run a 5-stage continuous reliability, security, and schema audit of an MCP server or AI agent endpoint.
- `actionguard\_check\_drift`: Verify whether an MCP server's tools schema or descriptions have drifted from a pinned Dual-Hash.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html