探索优秀的 AI 智能体 MCP 服务器

Edit code with high performance and multiplayer collaboration.

Automates coding tasks directly within your IDE using AI, capable of creating/editing files, executing commands, and using the browser with user permission.

Enables users to interact with multiple large language model (LLM) providers through a single desktop client.

Self-host a privacy-first, versatile ChatGPT alternative supporting multiple AI models and advanced features.

Automates complex development tasks using an extensible, open-source AI agent.

A cross-platform AI assistant and Model Context Protocol (MCP) client that connects to various services and local knowledge bases.

Interact with Ollama models directly from your terminal using a straightforward text-based client.

Interact with AI models using the Model Context Protocol through a cross-platform chat client.

Provides a desktop AI assistant that supports various LLM providers and offers features like prompt anywhere, AI commands, and document chatting.

Enables users to chat using various LLM APIs and productivity tools through the Model Context Protocol (MCP).

Enables interaction with LLMs and MCP-compatible servers from the command line.

Orchestrates AI models, Model-Context-Protocol (MCP) servers, and complex workflows through a unified interface.

Connects VSCode's Copilot Chat to MCP servers, enabling access to tools and resources.

Demonstrates integrating the Model Context Protocol (MCP) into a CLI chatbot.

Enables terminal-based AI conversations with support for multiple AI models and MCP client integration.

Netdata - Discovery, exploration, reporting and root cause analysis using all observability data, including metrics, logs, systems, containers, processes, and network connections

mcp-server-fetch is an MCP server that empowers AI agents to fetch and process web content using methods like browser automation, OCR, HTML scraping, and document parsing. It outputs clean markdown and intelligently selects the best extraction method.

Daytona - Fast and secure execution of your AI generated code with Daytona sandboxes

SafeLine - SafeLine is a self-hosted WAF(Web Application Firewall) to protect your web apps from attacks and exploits.

MCP Toolbox for Databases - Open source MCP server specializing in easy, fast, and secure tools for Databases. Supports AlloyDB, BigQuery, Bigtable, Cloud SQL, Dgraph, MySQL, Neo4j, Postgres, Spanner, and more.

Klavis ReportGen - Create professional reports from a simple user query.

Vizro - Tools and templates to create validated and maintainable data charts and dashboards

Lingo.dev - Make your AI agent speak every language on the planet, using Lingo.dev Localization Engine.

The langchain‑mcp‑adapters library bridges Anthropic’s Model Context Protocol (MCP) and LangChain/LangGraph. It converts MCP tools into compatible agents, connects across multiple MCP servers, and supports diverse transports like stdio and streamable‑HTTP.

Tianji - Interact with Tianji platform whatever selfhosted or cloud platform, powered by Tianji.

Exa - Search Engine made for AIs by Exa

Supabase - Interact with Supabase: Create tables, query data, deploy edge functions, and more.

Perplexity - An MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.

Nx - Makes Nx's understanding of your codebase accessible to LLMs, providing insights into the codebase architecture, project relationships and runnable tasks thus allowing AI to make precise code suggestions.

Grafana - Search dashboards, investigate incidents and query datasources in your Grafana instance

Netdata - Discovery, exploration, reporting and root cause analysis using all observability data, including metrics, logs, systems, containers, processes, and network connections

mcp-server-fetch is an MCP server that empowers AI agents to fetch and process web content using methods like browser automation, OCR, HTML scraping, and document parsing. It outputs clean markdown and intelligently selects the best extraction method.

Build AI applications that can learn and answer questions over large-scale federated data sources using a federated query engine.

Fetches up-to-date documentation and code examples for LLMs and AI code editors directly from the source.

Conducts in-depth web and local research on any topic, generating comprehensive reports with citations.

Daytona - Fast and secure execution of your AI generated code with Daytona sandboxes

Enables advanced automation and interaction capabilities with GitHub APIs for developers and tools using the Model Context Protocol.

Streamline AI-driven development workflows by automating task management with Claude.

SafeLine - SafeLine is a self-hosted WAF(Web Application Firewall) to protect your web apps from attacks and exploits.

Automates browser interactions for Large Language Models (LLMs) using Playwright.

Builds fullstack AI agents leveraging Google Gemini models and LangGraph for advanced web research and conversational capabilities.

Builds and queries temporally-aware knowledge graphs tailored for AI agents operating in dynamic environments.

Facilitates the creation of Model Context Protocol (MCP) servers with a Pythonic interface.

Browser MCP (by UI-TARS) - A fast, lightweight MCP server that empowers LLMs with browser automation via Puppeteer’s structured accessibility data, featuring optional vision mode for complex visual understanding and flexible, cross-platform configuration.

Provides a unified framework for building enterprise Retrieval-Augmented Generation (RAG) pipelines with small, specialized models.

Build AI applications that can learn and answer questions over large-scale federated data sources using a federated query engine.

Fetches up-to-date documentation and code examples for LLMs and AI code editors directly from the source.

Conducts in-depth web and local research on any topic, generating comprehensive reports with citations.

Enables advanced automation and interaction capabilities with GitHub APIs for developers and tools using the Model Context Protocol.

Streamline AI-driven development workflows by automating task management with Claude.

Automates browser interactions for Large Language Models (LLMs) using Playwright.

Builds fullstack AI agents leveraging Google Gemini models and LangGraph for advanced web research and conversational capabilities.

Builds and queries temporally-aware knowledge graphs tailored for AI agents operating in dynamic environments.

Facilitates the creation of Model Context Protocol (MCP) servers with a Pythonic interface.

Browser MCP (by UI-TARS) - A fast, lightweight MCP server that empowers LLMs with browser automation via Puppeteer’s structured accessibility data, featuring optional vision mode for complex visual understanding and flexible, cross-platform configuration.

Provides a unified framework for building enterprise Retrieval-Augmented Generation (RAG) pipelines with small, specialized models.

Automates browser-based workflows using LLMs and computer vision for robust and adaptable web interactions.

Connects Blender to Claude AI, enabling prompt-assisted 3D modeling, scene creation, and manipulation.

Facilitates building and deploying fully-managed AI agents and long-running workflows with built-in durability and observability.

Autonomously builds, refines, and optimizes other AI agents using an advanced agentic coding workflow and framework knowledge base.