3309 Model Context Protocol servers — searchable, rated, ready to install.
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Other AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
OSINT MCP server — 23 tools: DNS, WHOIS, Shodan, breaches, GEOINT, crypto. Works with Claude Code.
MCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1.
Lean MCP server for Google's Nano Banana (Gemini) image models. Returns file paths, not base64.
MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.
On-brand image generation (product shots, app icons, OG cards, sprites) for AI coding agents.
Model Context Protocol (MCP) for Hellō Admin API.
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
Cross-session memory for Claude Code — context capture, semantic search, recall
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
Manage your Claude Code MCPs by talking to Claude — list, restart, wrap, and more.
Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.
High-performance audio, music, and voice generation MCP server for Gemini 2.5 and Lyria 3.
Model Context Protocol server that lets LLMs collaboratively drive tmux
SmartGuard MCP Server - AI-powered smart contract security audit tools for Claude Code, Cursor,...
MCP Server for Optics Design System documentation and token usage.
MCP server for clinical charting with Claude - document patient visits to EMR
Query, report on, and optionally modify any Odoo ERP from Claude. Read-only by default.
Financial reasoning infrastructure for AI agents: typed models, deterministic compilation, receipts
Organize Claude Code memories, skills, MCP servers, commands, agents, rules via drag-and-drop.
Claude searches real job boards, scores each job 0-100 for fit, and shows a ranked board.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
POST /mcp