2449 Model Context Protocol servers — searchable, rated, ready to install.
AI dev tools + image generation, paid per-use with USDC on Base (x402).
Audio guides for 44,000+ places in 1,900+ cities, with narrated previews in ChatGPT and Claude.
Image, video, music and text generation across 100+ models through one endpoint.
Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.
Scans datasets/models for PII/secrets, redacts, and packages a public-release bundle via MCP.
Consensus 'best X for Y' rankings from ChatGPT, Claude, Gemini & Grok. Search, verdicts, history.
Analyze LLM API costs: token waste detection, caching savings estimates, model comparison
Self-hosted MCP server for time-series forecasting and tabular ML via foundation models.
Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys.
Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.
Local MCP canvas for Modellix image generation, editing, task recovery, and visual project work.
Virtual try-on and on-model AI fashion photography: catalog search, try-on grids, HD delivery.
Build, simulate and calibrate JAX block-diagram models of hybrid dynamical systems.
Photo to technical drawing, CAD-ready DXF and DWG, 3D models and product renders.
Live SEO workflow tools for Claude Code, Codex, and AI agents.
Create forms, read submissions, and build invitations from Claude, ChatGPT, or any MCP client.
AI Linux & Windows server management with Claude MCP and fully private agents using local AI
Convert web pages or HTML to clean Markdown for LLM context. Local, no external API calls.
Put 3D models in someone's real room: generate, arrange, and hand back one AR link.
Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
MCP server exposing the Alibre PDM vault API: safes, projects, files, properties, versions.
BitTorrent-style mesh for AI inference across agentic CLIs. Local-first.
Container load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in the chat.
Owned, portable working memory: a plain-files markdown brain any model can read and cite.
POST /mcp