3143 Model Context Protocol servers — searchable, rated, ready to install.
Monte Carlo NFL, MLB, NHL, NBA and soccer odds, plus model-vs-market edge from live prices
Generate images and video from text prompts across Gemini, OpenAI and Kie AI.
Market forecasts with their own track record, inside Claude, ChatGPT and other MCP apps.
Transcribe Russian audio and video with timestamps and optional speaker labels from files or links.
Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Generate images, video, music, speech and text with 60+ models through your MostAI account.
User-approved phone calls, speech, transcription and voice agents with PyAI OAuth.
Instruments for what a model cannot know on its own: time, randomness, DNS, hashes, receipts.
Leanroute MCP: route to 13 LLM providers, check pricing/usage/credit, manage keys from any agent.
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.
Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
Escáner GEO: analiza si una web es legible y citable por ChatGPT, Perplexity, Gemini y Claude.
Lets one coding agent talk to another: Claude Code, Codex or Grok
Commission a multi-model AI spec committee from your agent; get rubric-scored, build-ready specs.
Image, video, audio and chat from 61 AI models through one connector. Pay per use, no subscription.
3D bin packing for freight in Claude & ChatGPT: cartons and pallets, the fit, a 3D plan in the chat.
Construct, inspect, visualize, and simulate evidence-backed ODE models with BioMASS
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Simulate cloud infrastructure and estimate cost before deploying or changing infrastructure.
Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.
VESA pattern, dimensions and weight per TV or monitor model, from the makers' manuals. Read-only.
Dead-man's switch for Anthropic API spend: kills the key the instant it crosses a limit you set.
Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.
POST /mcp