3309 Model Context Protocol servers — searchable, rated, ready to install.
Animica chain data, free keyless AI inference, quantum randomness, x402 discovery, mining stats.
LLM Observability & Orchestration Agent
Claude Schema Output Agent
Generate AI images and videos from 89 models on one credit balance, refunds on failure.
BitTorrent-style mesh for AI inference across agentic CLIs. Local-first.
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
MCP-Native LLM Orchestration Agent
Local-first RAG MCP server: hybrid search over a folder of your own documents
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Live SEO workflow tools for Claude Code, Codex, and AI agents.
Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor
Search and download sprites, models, textures, and sounds from VG Resource.
Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
Selects the minimum code an LLM needs to review a git diff
Local-first RAG engine with MCP server for AI agent integration.
Search remote Model Context Protocol servers and tools discovered by BuiltWith, without an API key.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Renders Mermaid diagram syntax to PNG or SVG images for LLM clients
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
AI Linux & Windows server management with Claude MCP and fully private agents using local AI
Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys.
Track AI visibility (ChatGPT, Gemini, AI Overviews), research SEO keywords, write, publish, prove.
Read-only catalogue search: JVM tooling, ML models, compliance APIs, siSwati LLM, Veridix markets.
Pay-per-call NLP & embeddings APIs on Base via x402. No keys/signup; agents pay per call in USDC.
POST /mcp