3394 Model Context Protocol servers — searchable, rated, ready to install.
Flashcards for Claude: create, edit and study StudyCards decks with FSRS spaced repetition.
Autonomous coding pipeline: frontier models plan and review, open-weight models write the code.
Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.
Delegate summarising, extraction, classification and OCR to the macOS 27 on-device model.
Citepath public MCP server for LLM readiness audits and public scan results.
Computer use for Claude Code, Codex, Cursor or any MCP client: your computer + Android phone (beta)
LinkedIn MCP for Claude, ChatGPT, Grok, Hermes: triage inbox, comment, find people, live profiles
Ask the human for API keys in a browser page and write them to .env. The model only sees key names.
Feedlio MCP server exposing posting and scheduling tools to Claude Desktop and Claude Code.
Second opinion for agents: 3-4 AI models answer, one verdict with confidence and dissent.
Reads a migration, Prisma schema, Django model or TypeORM entity and marks every column a subject ac
Operational NWP, ensembles, AI weather models, regional forecasts, history, and verification.
Check an IP or your own network exit before using ChatGPT, Claude, Gemini or Meta Muse.
Microsoft Teams for Claude — read any chat or channel and its unread messages; send and react
Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.
A calorie MCP that looks up calories and macros from a 4M+ food catalog, not model guesses.
Compile any codebase into a walkable graph and serve it over MCP. No model decides an edge.
Test FIX from Claude, ChatGPT, or Cursor: free sandbox FIX sessions or your own FIXSIM instances.
Local stdio MCP for OpenAI-compatible and Gemini image generation, editing, and model fallback.
Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.
Build, edit and publish websites from Claude, ChatGPT, Cursor and Gemini. No code — Zarla hosts it.
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
Consistent prompts for one human character across image and video models. Paid per call, x402.
Enforce AI budgets before the model call and track cost per customer across 10 providers.
POST /mcp