3230 Model Context Protocol servers — searchable, rated, ready to install.
Read-only: which LLM is best in 7 languages (zh, ko, nb, de, nl, es, pt), from public benchmarks.
Cheapest API for any model across official, inference and relay providers; find free credits
System-automation agent MCP server for opencode/claude/pi: guarded shell, dry-run-first, audited.
Hosted Notion MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
AI model shutdown dates, replacements, and migration diffs. Free, no API key.
NHL on Kalshi: tonight's games and goal scorers vs a model, plus Stanley Cup odds vs Polymarket.
Hosted OpenAI Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs
Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes).
Insurance brokers: get meetings with retail producers and CFOs using Claude.
A film studio inside your own Claude, better every day. Films, voices and music on your own keys.
Tailor your resume to any job, get an ATS score and download the PDF from ChatGPT or Claude.
Make short videos in Claude or ChatGPT: remake a winning TikTok, or change who or what is in yours.
Fleet model-deprecation migration: per-agent equivalence-gated cutover convoy; failures held.
Publish HTML from Claude, ChatGPT, Gemini or any MCP client and get a shareable link. No account.
Brand visibility in ChatGPT, Gemini, Perplexity and AI Overviews: mentions, sources, GEO tips.
Hosted Slack MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Create and update subscription calendars from ChatGPT, Claude, or Codex.
Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM pro
A shared board your Claude projects read and write: handoffs, @mentions, pinned notes.
Adaptive multi-tier TPM/RPM rate limiter with smooth leaky bucket queuing and burst wait estimation
Local, private long-term memory for AI: verbatim, searchable, correctable. No LLM or API key.
Make how-to videos, social clips and help articles from Claude or ChatGPT, and run your help center.
Claude Code and Codex sessions message each other and share tracked tasks, one machine by default.
POST /mcp