io.github.stand-out-of-my-sun/diogenes-gemini-suite-mcp · v1.0.0 · ai-and-media
Diogenes Gemini Suite & Agents MCP is healthy: it completed an MCP handshake in 288 ms and exposes 20 tools.
Account-less MCP access to 45 Gemini models & autonomous agents via L402, x402, and MPP.
Endpoint: https://diogenes-micro-gateway.corinth.workers.dev/mcp/gemini-suite (streamable-http)
Repository · Website · JSON · Add to my inventory
| Users (last 30 days) | 0 |
| Handshake | Healthy |
| Auth needed | None |
| Tool count | 20 |
| Latency | 288 ms |
| Last checked (UTC) | 2026-10-20T16:11:08.372Z |
| Checked (UTC) | Status | Latency | Error |
|---|---|---|---|
| 2026-10-20T16:11:08.372Z | Healthy | 288 |
x402_embeddings | Agent Semantic Vector Embeddings ($0.01 USDC via x402). |
mpp_session_infer | Streaming Agent Reasoning & Session Inference ($0.05 USDC via MPP). |
mpp_deep_search | Deep research dossier with live citations ($0.10 USDC via MPP on Base). |
ai_code_gen | Python Script & Scraper Synthesis using Gemini models (300 sats via L402). |
ai_extract | Structured JSON Entity Extractor from arbitrary unformatted text (150 sats via L402). |
ai_summarize | Executive technical summarizer and brief generator (100 sats via L402). |
ai_antigravity_agent | Google Antigravity autonomous agent with remote execution and tool use (500 sats via L402). |
ai_deep_research | Deep Research Pro multi-hour investigative analysis engine (1000 sats via L402). |
ai_computer_use | OS-level desktop, GUI, and browser automated interaction agent (800 sats via L402). |
ai_generate | Universal Tier 1 model generator supporting 45 foundation models (250 sats via L402). |
ai_image_gen | Photorealistic and vector asset generation via Nano Banana / Pro (350 sats via L402). |
ai_tts | Natural expressive voice synthesis across Gemini TTS models (200 sats via L402). |
ai_music_gen | Musical composition and instrumental audio generation via Lyria (500 sats via L402). |
ai_video_gen | High-definition cinematic video synthesis via Veo 3 (1500 sats via L402). |
ai_audio_live | Direct audio-to-audio conversational intelligence without STT/TTS cascade (300 sats via L402). |
ai_omni | Unified multimodal model handling simultaneous text, audio, and video (300 sats via L402). |
ai_robotics | Spatial reasoning, kinematics trajectory calculation, and robotics task planning (450 sats via L402). |
ai_embeddings | High-dimensional 3,072-vector text embeddings for semantic search (50 sats via L402). |
ai_grounded_search | Frontier reasoning grounded directly in live Google Search results (200 sats via L402). |
ai_grounded_maps | Grounded reasoning with live Google Maps place details and spatial context (250 sats via L402). |