AI & Agents MCP Servers for Claude Desktop

A powerful MCP server providing access to multiple AI models (Grok, Gemini, Kimi, Qwen, GLM) through OpenRouter. Perfect for Cursor, Claude

Auto-loads skills into agent sessions. MiniMax vision and search proxy.

AI coding agent orchestration at scale. Karpathy optimization loops, multi-agent pipelines, DAG dependencies, autoscaling workers. Claude

Boundary MCP - a decision-making thinking engine that exposes reality's structure rather than giving advice

Reusable MCP server + Chinese RAG pipeline toolkit (factory + Tool builder + error envelope + eval framework). Powers @yiong/mcp-hr

Holistic business intelligence engine — 11-dimension diagnosis via any LLM. Triple option (Paid/OSS/CIA)

Multi-agent orchestration with loop prevention, contribution scoring, and MCP integration

MCP server to search, install, and offer Claude skills from Comptaskill (comptaskill.fr).

MCP server for AI cost optimization with prompt complexity classification

Epistemic guard for AI coding: tracks uncertain values and blocks writes until verified.

MCP server discovery - find and install MCP servers from Official Registry, Glama, and Smithery

Checks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.

MCP server that transforms linear AI reasoning into structured, auditable thought graphs

MCP server implementing dual-cycle metacognitive reasoning framework for autonomous agents

MCP server for the Entire CLI — manage AI agent checkpoints and sessions

🛡️ Make AI interrupt itself and challenge your thinking. Turns Claude into a philosophical sparring partner who actively contradicts

MCP server for connecting AI agents to Flowise instances

Gemini Enterprise Model Context Protocol (MCP) Server

Search and install 3,000+ AI skills from getskillsai.org into Claude Code, Cursor, ChatGPT.

AI inference pricing for agents: live and historical model prices, provider comparison.

MCP server for interleaved sequential thinking with dynamic tool calling, host-delegated execution, and self-monitoring quality signals