3073 Model Context Protocol servers — searchable, rated, ready to install.
Catches leaked credentials and PII in outbound LLM prompts
Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.
Genealogical research in the US National Archives Catalog: records, transcriptions, page images.
Build, edit and publish websites from Claude, ChatGPT, Cursor and Gemini. No code — Zarla hosts it.
Feedlio MCP server exposing posting and scheduling tools to Claude Desktop and Claude Code.
Forge designed Power BI projects (.pbip) from your agent, bound to your own semantic model.
Live crypto cycle data: 48-signal Bitcoin cycle model, Bitcoin ETF flows, ASX ETFs, altseason
Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
Accessible maidr charts in ChatGPT and Claude, explored by sound, braille and screen reader
Wallet auth: send a wallet and conditions, get a signed boolean across 37 chains.
AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…
Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.
Drive Google Flow from an agent: Veo video and Imagen image generation
Check whether ChatGPT, Perplexity and Gemini recommend a business. By Cited (cited.voreli.ai)
台本を渡すとゆっくり解説・ずんだもん解説の動画（MP4）が返る。音声合成・字幕・図解・BGM・効果音まで自動。ChatGPT / Claude からは OAuth でつなぐだけ。
Local Claude Code and Codex sessions on one machine exchange letters through native inputs.
Manage Nextcloud tasks, calendar events and notes from Claude over CalDAV and the Notes API.
Give Claude a whiteboard: notes, links, images and diagrams on a board you both see and edit.
Bulk YouTube transcripts from videos, channels, playlists or search: text, RAG chunks, SRT, VTT.
Shared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.
Token guard and rate limiter preventing runaway API cost spikes for OpenAI and Anthropic.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.
Observability for AI apps: investigate traces, logs, LLM usage, replays and crashes; manage alerts.
POST /mcp