3394 Model Context Protocol servers — searchable, rated, ready to install.
Generate and edit images, video, voice, lip-sync and 3D models from your AI agent.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
Read-only SQL Server diagnostics for LLM agents: Query Store, waits, plans, indexes
Local Claude Code and Codex sessions on one machine exchange letters through native inputs.
Convert JSON samples into TypeScript interfaces and Zod schemas, with inference caveats.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Read, search, move, and delete Yahoo Mail over IMAP — MCP server for Claude
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Let a model explore AKShare's 1000+ China market data functions on its own — search, inspect, call
Maths a model gets wrong: units with dimensional checking, equations, sheets. 5 tools, local.
Revit tools over MCP stdio. Actions are enabled by default; the workstation lock disables them.
Local MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline
Check npm dependencies for outdated majors, and see which dev tools AI models pick.
Start a NorthernGo cloud build from Cursor, Claude or Codex. EU database included.
Stock price forecasting for China A-shares — Kronos K-line time-series model
AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…
Audit an MCP config, price a model, size a GPU, explain network config drift. Key-free.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
Create, edit, render, save, and export voxel models with interactive 3D previews.
Israeli car data by plate or model, licence fee, recalls, thefts and car-insurance facts.
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.
Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
POST /mcp