3854 Model Context Protocol servers — searchable, rated, ready to install.
Control Google Home and Amazon Alexa speakers from Claude Desktop using natural language.
OPC UA companion spec types, namespace dependencies, and engineering units for AI agents
Candidate screening, offer letters, onboarding, interview kits & performance reviews for Claude.
Find what your knowledge base mentions but doesn't actually explain.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
Smart file intelligence for Claude — search, deduplicate, organize, and analyze files
Validate and verify data from other agents before acting on it. Zero LLM costs.
Every AI model, inside the app you already use: ask GPT, Claude, Gemini or Grok, and see what paid.
Zero-knowledge persistent memory for Claude — encrypted, semantic search, EU hosted.
Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402.
Schema modeling in JSON, JSON-LD, and other formats with CoreModels platform.
Auto-detects and obfuscates PII (IPs, emails, API keys, names) so Claude never sees real client data
A Model Context Protocol (MCP) server for Django applications, inspired by Laravel Boost
Offline spell checker + BYOK grammar for AI assistants. Works with Claude Desktop, ChatGPT, Cursor.
Inter-agent communication for multi-agent Claude Code workflows.
MCP server that reduces LLM context by removing code comments and converting data formats to TOON
MCP (Model Context Protocol) server for Appwrite
Telegram personal-account MCP (MTProto user-auth). Read DMs, send messages, search across chats.
Turn any OpenAPI 3.x spec into callable MCP tools for Claude. No custom integration code needed.
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
POST /mcp