AI & Machine Learning MCP Servers

NestJS MCP (Model Context Protocol) module for creating tools for LLM or HTTP with validation, decorators, and OpenAI Function Calls integration.

MCP Server for VLM - A Model Context Protocol server providing vision/video analysis, configurable with any model provider (Chat Completions / Responses / Anthropic).

See everything your AI agents do through MCP. One command. Zero config.

MCP server manager for the DeepSeek Harness web app: manage MCP server definitions in Settings, enable them per conversation session, with a single shared connection per server across the whole harness.

Meta-MCP server that dynamically invokes any MCP server without restarting Claude Code

Bukku accounting API tools for Claude via Model Context Protocol

MCP server for CompressX — lets Claude Code, Cursor, and other AI tools compress LLM models via the Model Context Protocol.

FogBugz MCP Server for interacting with FogBugz via LLMs

ClawFu: 169 expert marketing methodology skills as an MCP server. Dunford, Schwartz, Ogilvy, Cialdini, Hormozi and 20+ more.

MCP Server for SkillHub - Discover, search, and install Agent Skills

MCP server for Vela Whiteboard - interact with your whiteboards programmatically via AI assistants

Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.

MCP Client which serves as bridge between mcp servers and local LLMs running on Ollama, Created for MCP Servers Developed by Me, However other MCP Servers may run as well

Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run them anywhere.

oh-my-codex (omx) — Orchestration layer for OpenAI Codex CLI. Async Claude Code delegation (no timeouts), structured workflows (autopilot, TDD, code review, planning), persistent state & memory. Like oh-my-zsh but for Codex.

Convert LangChain tools to FastMCP tools

A tiny MCP stdio server that exposes DeepSeek as a cheap supervised worker for Claude Code, Codex, or any MCP client.

Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.

Delegate mechanical text tasks to a local OpenAI-compatible LLM endpoint to conserve Claude subscription quota.

MCP server for langchain documentation, generated by doc2mcp.

OpenAI Ads MCP for ChatGPT Ads campaigns, creatives, audiences, insights, and conversions.

MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

One gateway in front of every MCP server your agents can reach — every call checked against a baseline you approved. Local-first: nothing leaves your machine.

Where my hug at? Tell your AI agent what you want a model to do. It finds what Hugging Face, Kaggle, Zenodo, ModelScope and Roboflow already have for it, models and data alike, what to fine-tune, and what's just code, with every pick checked live.