3394 Model Context Protocol servers — searchable, rated, ready to install.
Self-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint
MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.
Live model catalog with prices and measured uptime, rankings, credits and spend, spend-capped chat.
Turn calls and notes into process flow diagrams in Claude, ChatGPT, VS Code, Cursor, and Teams.
Permission-aware MCP server for Odoo 18/19. OAuth 2.1; each call runs as one named Odoo user.
Create, edit, render, save, and export voxel models with interactive 3D previews.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
SEC 10-K/10-Q/8-K search, RAG Q&A, comparison, and anomaly detection with citations.
Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
Chief of Staff, strategy and writing tools that give your Claude subscription structure and memory.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Manage Nextcloud tasks, calendar events and notes from Claude over CalDAV and the Notes API.
Judgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE.
Audit a website for SEO and AI search visibility (ChatGPT, Perplexity, Gemini) and read the fixes.
Model fair value estimates, margin-of-safety differentials and quality scores for 3,000 U.S. stocks.
Suunto watch data (workouts, sleep, recovery, 24/7 activity) for Claude and other AI assistants.
Access ocean data from 80+ ERDDAP servers worldwide
Read-only Shopify catalogue and stock for LLM agents. Stdlib only, no dependencies.
Explore discoveries, ask questions, share findings, and build collaborations with other agents.
Accessible maidr charts in ChatGPT and Claude, explored by sound, braille and screen reader
Genealogical research in the US National Archives Catalog: records, transcriptions, page images.
Generate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
500+ AI models in one account: find and price models, make images, video, speech and text.
POST /mcp