Home / MCP registry index / dev.agentdiet/prompt-guard
AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall
dev.agentdiet/prompt-guard in the official MCP registry.
Endpoint https://prompt-guard.agentdiet.dev/mcp. Source: github.com/robertoyanguas-ops/assay.
The registry describes it as: Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
We read its 2 tools on 2026-10-22. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
scan_prompt_injection get_agent_wallet_status
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/dev-agentdiet-prompt-guard)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.