3281 Model Context Protocol servers — searchable, rated, ready to install.
Search AO3 and have fics read by a secondary model before they're recommended
Authenticated MCP Agent (Openai)
MCP server for vertical datum conversions using coastalmodeling-vdatum
Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
Forge orchestrator MCP server for Claude Code (alpha). Codex/Gemini runners are not in the alpha.
The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
Convert a web page URL to clean Markdown for LLM context. Local, no external API calls.
Memory MCP server for Claude Code. Correct a fact and the old version stops being recalled.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key.
Scans datasets/models for PII/secrets, redacts, and packages a public-release bundle via MCP.
Your Garmin golf data in Claude: GPS shots, strokes gained, club distances, health context
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Muse AI Image turns prompts into photoreal pictures and clips with the Muse Image model and Muse
One workspace of tools for Claude and ChatGPT: connect 600+ apps, generate media, build tools.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
My Hot Lunchbox school lunch ordering for Claude — calendar, cart, orders, payments
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Multi-model weather forecasts: point series, model scoreboard, and gridded fields. No auth.
Managed Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers
Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.
POST /mcp