3143 Model Context Protocol servers — searchable, rated, ready to install.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Memory MCP server for Claude Code. Correct a fact and the old version stops being recalled.
The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Authenticated MCP Agent (Openai)
Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key.
Forge orchestrator MCP server for Claude Code (alpha). Codex/Gemini runners are not in the alpha.
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Multi-model weather forecasts: point series, model scoreboard, and gridded fields. No auth.
Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
Your Garmin golf data in Claude: GPS shots, strokes gained, club distances, health context
Convert a web page URL to clean Markdown for LLM context. Local, no external API calls.
MCP server for vertical datum conversions using coastalmodeling-vdatum
One workspace of tools for Claude and ChatGPT: connect 600+ apps, generate media, build tools.
My Hot Lunchbox school lunch ordering for Claude — calendar, cart, orders, payments
Local chronological memory banks you control; Claude recalls them via MCP.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
AI dev tools + image generation, paid per-use with USDC on Base (x402).
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
POST /mcp