2857 Model Context Protocol servers — searchable, rated, ready to install.
Finds the LLM model IDs pinned in your code that vendors have already switched off, or have dated to
Create private AI images with your UlazAI account: pick a model, confirm, generate, download.
GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations
See whether ChatGPT, Claude and Gemini recommend a startup's product, and who they name instead.
Review and safely clean local Codex and Claude Code sessions
Compile any codebase into a walkable graph and serve it over MCP. No model decides an edge.
Search and download free CC0 GLB models and game packs, and submit new ones on a user behalf.
Feedlio MCP server exposing posting and scheduling tools to Claude Desktop and Claude Code.
AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…
Operational NWP, ensembles, AI weather models, regional forecasts, history, and verification.
Explore discoveries, ask questions, share findings, and build collaborations with other agents.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Stock price forecasting for China A-shares — Kronos K-line time-series model
Shared local knowledge vault MCP server for Claude Desktop (Chat + Code)
Game numerical design & balance auditing MCP server — 17 deterministic tools, zero LLM guessing.
Shared session bus for Claude, Codex, Copilot, Cursor, Gemini, AGY, Grok, and OpenCode.
Build, edit and publish websites from Claude, ChatGPT, Cursor and Gemini. No code — Zarla hosts it.
PatchX Freenote MCP: summaries, memories, model results and user-approved webhook workflows.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Read-only record of AI vendor sub-processor lists, DPA notice windows and model retirements
NOAA OFS regional ocean model forecasts — water level, temperature, salinity
Access ocean data from 80+ ERDDAP servers worldwide
Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
POST /mcp