3360 Model Context Protocol servers — searchable, rated, ready to install.
One workspace of tools for Claude and ChatGPT: connect 600+ apps, generate media, build tools.
Research Hadith, authenticity, grading, Takhrij and Sharh [commentaries] in Claude Desktop for free.
Muse AI Image turns prompts into photoreal pictures and clips with the Muse Image model and Muse
Analyze LLM API costs: token waste detection, caching savings estimates, model comparison
AI dev tools + image generation, paid per-use with USDC on Base (x402).
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Encrypted OAuth LLM Agent
Connect Claude to your Gmail and Outlook inbox. Read, search, and manage emails via AI.
SWAT+ watershed models for any river in the lower 48 states, with groundwater and PFAS data
Approved acceptance criteria served over MCP to Claude Code, Cursor, or Codex. Git-only, sealed.
Self-hosted MCP server for speech: ASR transcription, TTS synthesis, and file staging tools.
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
Test whether 3D assets survive Apple Quick Look and Safari <model>, then fix what fails
Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.
Authenticated LLM Traced Agent
Live used-car stock on named NZ dealer yards. Search make, model, price, city. Not Trade Me.
Scans datasets/models for PII/secrets, redacts, and packages a public-release bundle via MCP.
Measured AI-inference-storage benchmarks with citations, article search, KV-cache ROI estimation.
Sourced market and compliance research for Claude Desktop, Claude Code and Cursor.
Authenticated LLM MCP Agent
Run 70+ AI models and 50+ tools on CNAPS Studio in natural language — Claude, n8n, or Zapier.
Self-hosted MCP server for time-series forecasting and tabular ML via foundation models.
POST /mcp