3002 Model Context Protocol servers — searchable, rated, ready to install.
Run commands with API keys injected per call — values never enter model context.
Local Markdown search, navigation and editing via MCP, with optional vector embeddings.
Code review by AI models from different companies, usually two. Shows where they agree and disagree.
Is it recalled? US recalls from 9 agencies by UPC, model, NDC, VIN or lot. Its API also takes x402.
Vehicle safety recalls from NHTSA by make, model, and year. No key required.
Generate AI video and images from your agent: Seedance 2.x, GPT Image 2.5, 172 prompt recipes.
Amazon Seller Central and Ads in Claude or ChatGPT. Connect at agentxray.ai/connect.
Your WhatsApp Business inbox in Claude or ChatGPT: who's waiting, follow-ups and replies.
x402-paid MCP tools: utils, audit screens, corpus search, inference. USDC Base+Solana.
GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
Generates 1200x630 OG social preview images (PNG/SVG). Tools: generate_og_image, get_quota.
Run WhatsApp AI agents: manage agents, conversations, CRM contacts, orders and RAG docs.
Landing A/B tests, Yandex Wordstat, Metrika, Direct and 170+ AI models in ChatGPT, Claude, Cursor
Read-only Garmin and Strava data for your AI: activities, sleep, HRV, readiness, training load.
Post all your social media with your AI agent — 9 networks, from Claude, ChatGPT or Cursor.
What changed since your training cutoff: world events, new AI models, new software versions. Free.
Order real 3D prints from chat: send an STL or OpenSCAD model, see one price, get it by UPS.
Checks a remote MCP server against the Claude directory rules and guides its publication.
Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
Notes and actions in one app. Let Claude or ChatGPT read and update them.
Your recorded Mac meetings in Claude: search, promises with owners, follow-ups. Local, read-only.
Compare Figma designs against live websites and get visual + content QA reports, from inside Claude.
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.
POST /mcp