2857 Model Context Protocol servers — searchable, rated, ready to install.
Permission-aware MCP server for Odoo 18/19. OAuth 2.1; each call runs as one named Odoo user.
Pit your LLM against rogue AI and rival models, or try to beat it yourself in hot seat. 3D tactics.
Search your local Claude Code archive. For continuous capture, use the Rootz Archive plugin.
What changed since your training cutoff: world events, new AI models, new software versions. Free.
One memory for AI agents in Claude Code, Cursor, Codex and ChatGPT that flags conflicting facts.
Software engineering firm in Serbia: services, engagement models, articles - and send an inquiry.
Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
Run commands with API keys injected per call — values never enter model context.
Send, receive and track real faxes in the US and Canada from Claude, ChatGPT or Cursor.
Ovanek MCP: Model Context Protocol server for Ovanek platform tools; writes are dry-run by default.
Your own WhatsApp in Claude and ChatGPT: read chats, draft replies, send messages you approve.
A decision model for the calls that don't have a right answer. The better option, with a reason.
Shared Markdown memory for Claude, ChatGPT, Claude Code and Codex. OAuth, no API keys.
Compound Labs: eight keyless lookups. Model pricing, dep health, stack cost, registries.
UI design MCP: design references, intent routing, anti-slop static detector and gate. No API key.
Log meals, water, and weight to Garmin Connect from Claude or ChatGPT.
Your recorded Mac meetings in Claude: search, promises with owners, follow-ups. Local, read-only.
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
Publish HTML/code from your agent to openanthropic.com and get a shareable link.
Manage your ZRouter AI gateway account: usage, logs, model routers, API keys, budgets, and limits.
Human-verified daily catalog of free and cheap AI model API credits and token promos.
Checks a coding agent's handback against the pull request's GitHub record. No model decides.
Score academic and professional writing against published criteria with three reference models.
Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
POST /mcp