3360 Model Context Protocol servers — searchable, rated, ready to install.
Describe your business. Get a beautiful website, built and published for you from Claude or ChatGPT.
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Ovanek MCP: Model Context Protocol server for Ovanek platform tools; writes are dry-run by default.
Records the prompt, model and files an agent declared for a line. It does not prove who typed it.
Prices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key.
Manage your ZRouter AI gateway account: usage, logs, model routers, API keys, budgets, and limits.
Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.
Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source
Access Pollinations models and API capabilities through agent tools.
Amazon Seller Central and Ads in Claude or ChatGPT. Connect at agentxray.ai/connect.
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
Safe folder access for ChatGPT and Claude: read, write and search files, risky tools opt-in.
Generate and edit images with GPT Image 2.5 for $0.029 — free key, 50 credits, no card.
How often ChatGPT, Perplexity, Gemini and Claude mention and cite your brand vs competitors.
Epoch AI — AI models database
UN Charter (1945, as amended) as an executable model with worked cases; not UN-affiliated
Model Context Protocol server for OpenText Software Delivery Platform.
Draft email campaigns in day3 from Claude Code, Cursor or VS Code as editable composer blocks.
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
Trade Papertrade BTC and ETH perps from Claude, ChatGPT, Codex, Cursor and any MCP client.
One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.
Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Find out which MCP servers you actually use: local, read-only audit of Claude Code transcripts.
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
POST /mcp