AI & Machine Learning MCP Servers
AI services, embeddings, LLM integration
2,891 servers
mlx-mcp-server
MCP server bridging Codex to local MLX LM (and any OpenAI-compatible backend)
skim-mcp
Token-efficient skim-then-expand I/O for agentic models (Claude Code / desktop Claude) via MCP
mcp-bastion-fireworks
MCP-Bastion security middleware for Fireworks AI. Prompt injection, PII, and rate-limit protection.
opentext-pa-mcp
MCP server that exposes an OpenText AppWorks Platform entity service to Claude (and other MCP-compatible clients) through a small set of generic, plain-English tools.
iflow-mcp_tomconte-codebox-ai
A secure Python code execution service that provides a self-hosted alternative to OpenAI's Code Interpreter
inferenceindexer-mcp
MCP server exposing InferenceIndexer pricing data as agent tools.
mcp-strict-check
Which of your MCP tool schemas a provider's strict mode would reject, at which JSON pointer, and what to change.
@justfortytwo/memory
Standalone semantic-memory MCP server (SQLite + sqlite-vec + Ollama embedder). persona-agnostic.
screenshot-feedback-hook-mcp
Screenshot feedback for coding agents — let your agent SEE what it builds (MCP server + Claude Code hook)
ollama-almasrv-mcp
MCP server for accessing Ollama models on a remote GPU server via Model Context Protocol
402ai-mcp
MCP server for 402ai.net - Lightning-paid OpenAI proxy tools
PrivaSearch
Search your own case files from Claude, ChatGPT or Mistral Vibe with personal data pseudonymised.
bing-webmaster-tools-mcp
Model Context Protocol (MCP) server for Bing Webmaster Tools & IndexNow API via NPX. Spawns the Python package through uvx with full stdio passthrough.
mcp-bastion-litellm
MCP-Bastion security middleware for LiteLLM (100+ LLM providers via one OpenAI-compatible API).
mcp-second-opinion
Let your MCP-aware agent consult rival LLMs (OpenAI, Gemini, Anthropic, Grok) mid-conversation.
comfyui-mcp
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),
memanto-mcp
Model Context Protocol (MCP) server for Memanto - persistent semantic memory for any MCP-compatible agent
@enderfga/claw-orchestrator
Claw Orchestrator — run Claude Code, Codex, Antigravity, Grok Build, OpenCode, any ACP agent and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol
mcp-rubber-duck
An MCP server that bridges to multiple OpenAI-compatible LLMs - your AI rubber duck debugging panel
@blockrun/mcp
BlockRun MCP Server - Give your AI agent web search, deep research, prediction markets, and crypto data. Paid via x402 micropayments.
octocode-mcp
Model Context Protocol (MCP) server for advanced GitHub repository analysis and code discovery. Provides AI assistants with powerful tools to search, analyze, and understand codebases across GitHub.
mcp-local-rag
Local RAG MCP Server - Easy-to-setup document search with minimal configuration
mcp-engine
SemanticOps MCP - Power BI MCP Server providing programmatic access to Power BI models via Model Context Protocol
claude-historian-mcp
an MCP server for Claude Code conversation history