3260 Model Context Protocol servers — searchable, rated, ready to install.
Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
Show holiday photos from Vercel Blob inline in Claude chats.
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
Find the right AI model for your job. Free discovery and ranking; tests on your own key.
Image generation & editing for AI agents (Runware) — text-to-image, bg removal, upscale.
LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM
Real-time NSE/BSE stock sentiment, news NLP, technical analysis & RAG search via MCP.
Run UX research from Claude — create card sort studies, list studies, pull headline stats.
Claude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps.
Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.
ADCIRC model configuration debugging, parameter lookup, and validation
Persistent cross-project memory for Cursor and Claude Code using local semantic search.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Search and browse every MCP server in the Model Context Protocol registry.
List LLM providers and run chat completions through the three.ws multi-provider router.
Explore the Claude Code CLI source — browse tools, commands, search code, and more.
IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.
A Model Context Protocol server implementation for Nx
Candidate screening, offer letters, onboarding, interview kits & performance reviews for Claude.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Biologically-inspired persistent memory engine for Claude Code MCP agents
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.
GPU-accelerated MCP server for neural network training, deep learning, and model experimentation
POST /mcp