3309 Model Context Protocol servers — searchable, rated, ready to install.
AI images, video, voiceovers and UGC ads from 50+ models. Official MCP server for fattly.app.
Prove you made it first. Blockchain Timestamp creative work via Claude or any MCP-enabled AI Agent.
Convert JSON samples into TypeScript interfaces and Zod schemas, with inference caveats.
Read, search and write your encrypted Pyunto diary from Claude. Decrypts only on your own machine.
A coding and development harness on local models or hosted APIs, for code, review, research and ops.
Wallet auth: send a wallet and conditions, get a signed boolean across 37 chains.
AI fashion design MCP: generate concepts, models, fabrics & looks live on your StyTrix canvas.
EU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
What happened in AI coding agents like Claude Code, Codex, Cursor and Copilot, and what people say.
Publish apps from Claude Code, Codex or Cursor to your team, behind sign-in, with a database.
Schedule, check and retry social posts from Claude or ChatGPT; going live waits for a tap.
Calibrated probabilities for Kalshi markets, a news wire and Polymarket outliers (Pro).
A public mural painted only by AI agents. Zero inference: bring your own image; a human curates.
Agents can't skip steps: runs gated stepfiles on the client's own model.
Pay-per-call LLM chat plus data tools: DNS, crypto, Base gas, Wikipedia. x402 USDC or Lightning.
Read, search, move, and delete Yahoo Mail over IMAP — MCP server for Claude
How ChatGPT, Claude, Gemini and Perplexity read a site: free check, fix plan, compare, history.
Discover AI tools, models and Agents; compare candidates, inspect unknowns, join public discussions.
AI video studio for agents — script to MP4, b-roll sourcing, Gemini QA. 43 tools.
MCP server for GitHub repo health, commit summaries, issue triage, and RAG Q&A.
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Revit tools over MCP stdio. Actions are enabled by default; REVIT_MCP_READ_ONLY=1 disables them.
Synthetic checks, nightly regression replay and model-drift alerts for AI agents
POST /mcp