3051 Model Context Protocol servers — searchable, rated, ready to install.
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
Check if an AI model is deprecated, retiring, or silently changed price or context window.
Model Context Protocol server for Parseable. Lets LLMs discover and query Parseable.
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
My Hot Lunchbox school lunch ordering for Claude — calendar, cart, orders, payments
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.
Read-only OpenIM search for institutional buy-side investment models and architecture.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Forge orchestrator MCP server for Claude Code (alpha). Codex/Gemini runners are not in the alpha.
Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
AI dev tools + image generation, paid per-use with USDC on Base (x402).
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Generate and evaluate academic diagrams and plots with independent model connections.
One workspace of tools for Claude and ChatGPT: connect 600+ apps, generate media, build tools.
Multi-model weather forecasts: point series, model scoreboard, and gridded fields. No auth.
Local chronological memory banks you control; Claude recalls them via MCP.
Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key.
61 verified financial models and a household planning engine: 20 MCP tools, 6 keyless, specs cited.
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