3818 Model Context Protocol servers — searchable, rated, ready to install.
Premium agentic endpoint for cost-optimal-model-selector-mcp.
Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.
AI YouTube thumbnails from GPT Image, Nano Banana, FLUX and more, side by side. Pay per image.
Model Context Protocol server for Taiwan Legislative Yuan API v2.
QuickBooks Online in Claude and ChatGPT: 221 tools, full ledger, multi-company, Canada + US, FR/EN.
Consult Grok through xAI's metered API with exact model selection and no fallback
Give Claude complete understanding of your software project.
Low-poly 3D models and kits for three.js and game engines: search, match, remix, preview.
OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.
MAC address and OUI vendor lookup over Model Context Protocol.
Docs + source RAG for Pipe language: semantic search, cited answers, code symbol lookup.
Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
Search the Claude Code Ultimate Guide and machine-readable references from any MCP client.
Relays messages between two Claude Code sessions on different machines using the Channels API
Author, validate and maintain a CRAYON-C4 architecture model — never write an invalid file.
Simulate cloud infrastructure and estimate cost before deploying or changing infrastructure.
Self-hosted architecture model that agents read layer by layer, search, build and correct.
Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.
Rewrite AI-styled text into natural writing with a fine-tune model.
Independent measurements of how 12 AI models answer brand questions in Chinese and English.
Generate and edit images and video with MADE: model catalog with transparent per-job pricing.
Local privacy-first tools: redact secrets, decode JWTs, compare LLM costs. No network calls.
Plan and manage TravelOwl trips from ChatGPT, Claude and other MCP assistants.
GPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.
POST /mcp