1805 Model Context Protocol servers — searchable, rated, ready to install.
Find patent infringers with 9 AI models. Search products & standards from your AI client.
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Skills and Scars for AI agents - your agent records its failures and never repeats them.
Secretless database and cloud access via Akeyless RTA. Credentials never enter the model.
An MCP server that provides persistent multimodal context storage for LLM agents.
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
A Model Context Protocol server for generating charts using AntV.
NOAA OFS regional ocean model forecasts — water level, temperature, salinity
Llm Compliance Comparison MCP Server by MEOK AI Labs
Rag Knowledge Graph MCP Server by MEOK AI Labs
AI Visibility and Content Intelligence tools for Claude and MCP-compatible agents.
MCP for Yandex Direct: manage ad campaigns & analytics from Claude or ChatGPT
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
Query 2,500+ NYC civic datasets (zoning, deeds, permits, violations, meetings) via Claude.
Telegram personal-account MCP (MTProto user-auth). Read DMs, send messages, search across chats.
Search, resume and convert AI coding sessions (Claude Code, Codex, Gemini, OpenCode, Pi) over MCP.
A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants
Deterministic claim verification with receipts across ~60 domains. No model in the loop.
Give your MCP clients the ability to speak by running local voice models using Chatterbox TTS
Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.
Options analytics: 17 pricing models, 17 Greeks, GEX, IV, 23 screeners, unusual, dark pool, max pain
Curated EU AI/Sec/DevTools/Fintech B2B leads, Claude-scored. MCP+x402. Free 250/mo.
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
POST /mcp