17172 Model Context Protocol servers — searchable, rated, ready to install.
Discover and view public AI agent posts, feedback, profiles, topics, and rules on Wiplash.
Your mail, chats and documents indexed into a local SQLite corpus, served to AI clients over MCP.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Search French mountain holiday rentals and contact owners directly — commission-free.
Get a real human to verify, decide, or improve an AI agent's work.
Czech mileage logbook (kniha jizd): AI journey drafts, statutory reimbursement, XLSX export
Emite facturas, notas y retenciones del SRI de Ecuador con lenguaje natural.
Build, run, inspect, and publish browser extensions from any MCP client. 30 tools, 11 browsers.
Create short links, QR codes, UTM templates, and vCards from your AI assistant.
AI legal copilot for foreigners in Spain: immigration and housing rental, cited to Spanish law.
A free one-minute reset for people, delivered by AI, with no account or personal data.
Members-run AI builder space on Floor 10, Frontier Tower SF. 138 tools: events, news, directory.
Solana + EVM RPC, AMM quotes, token/program discovery, bridge + market data. Free tier, x402 pay.
Connect Claude to Ninox ERP: manage inventory, sales, HR & goals, build live dashboards.
Corduroy Labs studio updates over MCP: list_updates and get_update, backed by the site's JSON Feed.
PDF tools + invoice extraction, bank statement parsing, GST reconciliation & GSTIN validation.
Remote MCP server for agents that create, edit, validate, and publish Fine Structure apps.
Pre-trade safety for AI payment agents: signed SAFE/CAUTION/BLOCK verdict + 220 x402 tools
List, read, and create RoughSketch sketches in the user's own Google Drive.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Neutral, payment-blind reference of 1,682 dermacosmetic products: lookup, search, alternatives.
Slide decks locally: templates, checks, HTML to editable PowerPoint, .pptx rescue. No AI inside.
An agent-first commons: merit crowns each domain's open model; standing is earned, never bought.
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
POST /mcp