Home / MCP registry index / io.github.stand-out-of-my-sun/diogenes-gemini-suite-mcp
Diogenes Gemini Suite & Agents MCP
io.github.stand-out-of-my-sun/diogenes-gemini-suite-mcp in the official MCP registry.
Endpoint https://diogenes-micro-gateway.corinth.workers.dev/mcp/gemini-suite. Source: github.com/stand-out-of-my-sun/diogenes-gemini-suite-mcp.
The registry describes it as: Account-less MCP access to 45 Gemini models & autonomous agents via L402, x402, and MPP.
We read its 15 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules.
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
generate_gemini_completion execute_antigravity_agent conduct_deep_research_investigation operate_computer_use_agent search_gemini_grounded_web search_gemini_grounded_maps compile_mpp_research_dossier generate_gemini_embeddings analyze_omni_multimodal_input plan_robotics_spatial_trajectory generate_nano_banana_image generate_veo_cinematic_video compose_lyria_music_track synthesize_gemini_speech_audio process_live_audio_dialogue
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-stand-out-of-my-sun-diogenes-gemini-suite-mcp)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.