3444 Model Context Protocol servers — searchable, rated, ready to install.
Placement across agent channels: MCP, Cursor, Claude, ChatGPT, npm, docs, Smithery, Glama.
Checks a remote MCP server against the Claude directory rules and guides its publication.
Score academic and professional writing against published criteria with three reference models.
Read-only Garmin and Strava data for your AI: activities, sleep, HRV, readiness, training load.
AI image generation: characters, products, posters and edits, saved to your gallery.
Generate and edit images, video and audio: 300+ AI models, video tools, voice cloning, transcripts.
Control the free edition of DaVinci Resolve 21.1 from Claude through a Lua script inside Resolve.
Inspect 1NFER models, crypto funding terms and task cost without keys or paid calls.
Read-only ChinaAPI model catalogue, price snapshot, cost estimates and request recipes.
X/Twitter read API for agents: search, timelines, Smart Money. Claude/Cursor MCP. Not for posting.
Persistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB
Typed noul / choice / score judgments from a local Laya model, with token-budget preflight.
Hugging Face models and datasets. No key required for public data.
AI image generation and editing with Google Gemini: Nano Banana 2.1, Pro and Lite models
Give LLM agents webcam access: capture photos and record short videos over MCP.
UI design MCP: design references, intent routing, anti-slop static detector and gate. No API key.
Live registry of AI model specs, context windows, and per-token pricing.
Live review times for AI app stores: ChatGPT, Claude, Muse, Grok, Cursor. Check before you submit.
Give Claude, Cursor, or another AI assistant direct access to your QuickSnip library.
Notes and actions in one app. Let Claude or ChatGPT read and update them.
Crypto prices from Gemini. No key required.
Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.
POST /mcp