3281 Model Context Protocol servers — searchable, rated, ready to install.
LLM Observability & Orchestration Agent (Langchain)
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Claude Schema Output Agent
Live SEO workflow tools for Claude Code, Codex, and AI agents.
Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
AIO.GEO: audit, dry-run fixes, rescore, doctor. Remote + stdio. Not LLM rankings.
BitTorrent-style mesh for AI inference across agentic CLIs. Local-first.
Full-text search, browse, and resume across your coding agent sessions (Claude Code, Codex, Amp)
Container load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in the chat.
LLM Observability & Orchestration Agent
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.
Renders Mermaid diagram syntax to PNG or SVG images for LLM clients
Selects the minimum code an LLM needs to review a git diff
Search remote Model Context Protocol servers and tools discovered by BuiltWith, without an API key.
Local-first RAG engine with MCP server for AI agent integration.
Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys.
Local-first RAG MCP server: hybrid search over a folder of your own documents
AI Linux & Windows server management with Claude MCP and fully private agents using local AI
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.
Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
POST /mcp