3051 Model Context Protocol servers — searchable, rated, ready to install.
Search AO3 and have fics read by a secondary model before they're recommended
Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.
Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.
Search your AI chat history from Claude, Cursor, Codex, and other MCP clients.
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
PathCourse Health inference SKUs as x402 paid MCP tools, billed per call in USDC on Base.
AI-powered corporate learning platform — manage courses, users, and insights via Claude.
Authenticated LLM JWT Agent
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Official MCP server for Kaneo: manage tasks, projects, and labels from Claude and other MCP clients
Kia Access for Claude — vehicle status, location, doors, climate, and charging
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Self-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.
Create and manage Templated email templates from any MCP client - bring your own model.
AI-visibility monitoring for your brand across ChatGPT, Claude, Perplexity & Gemini.
Connect any AI to WordPress — content, media, SEO, WooCommerce, GA4, Search Console. 242 tools.
Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.
Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.
The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Check if an AI model is deprecated, retiring, or silently changed price or context window.
Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
POST /mcp