32939 Model Context Protocol servers — searchable, rated, ready to install.
Neutral, payment-blind reference of 1,682 dermacosmetic products: lookup, search, alternatives.
Get a real human to verify, decide, or improve an AI agent's work.
Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.
x402 pay-per-call infra for agents: $0.03 image generation, Postgres, auth, storage, functions.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Local semantic search over your Obsidian vault - always fresh, never reindex.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Full technical interview prep: company briefing, concepts, code deep-dive, mock interviews.
Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
Official ClickHouse MCP server for querying and exploring ClickHouse clusters and chDB.
Search and safely manage your private local Yaps Markdown vault from MCP clients.
Audit lead-delivery workflows, find reliability gaps, and generate a LeadProof integration plan.
Stateful Windows OpenSSH server operations for Codex with local credential handling.
An AI-powered, safe database access gateway built on the Model Context Protocol (MCP).
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
Choir management for AI assistants: events, RSVP, announcements and sheet music of your choir.
Emite facturas, notas y retenciones del SRI de Ecuador con lenguaje natural.
Medius docs: the binary control protocol, device behavior, and the medius Rust library.
Voyager's web-page sense: safe read-only observation of one live URL (structure, security, a11y).
Pay-per-query x402 business intelligence on Base, settled in USDC via the native 402 payment flow.
MCP server for AI agents to search major Chinese internet platforms with local-first login support.
CRM + visual automation builder AI agents can drive via MCP: contacts, tags, maps, email/SMS flows.
Preserve a user-authorized judgment and append later answers. No model verdict or human score.
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
POST /mcp