目录
目录README.md

Awesome MCP Servers Awesome

A curated, community-driven list of awesome Model Context Protocol (MCP) servers, tools, frameworks, clients, and utilities. MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations.


All Documents

Call for translators! We’re looking for translators to help translate this spec for everyone!

Read our documentation in the following languages:

Language Link
English English
简体中文 简体中文
繁体中文 繁体中文
日本語 日本語

What is MCP?

MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations. This list focuses on production-ready and experimental MCP servers that extend AI capabilities through file access, database connections, API integrations, and other contextual services.


Tutorials

Community


⚠️ Security Warning

When running MCP servers without proper sandboxing, they can execute arbitrary code on your system with the same permissions as the host process. This creates significant security risks.

Warning summary:

  • System Access: Full access to files, network, and system resources
  • Code Execution: Can run commands on your machine
  • Prompt Injection: Malicious prompts could trigger unintended server actions
  • Data Exposure: Sensitive data may be accessed or leaked

Best practices:

  • Use official implementations (marked with ⭐) when available
  • Run servers in VMs or isolated containers
  • Review code and configuration before installation
  • Limit permissions to the minimum required
  • Monitor server activity and logs

Examples of Supported Clients

Many MCP clients and UIs can connect to servers listed here. Examples include (but are not limited to):

  • Claude Desktop / Claude clients
  • Zed
  • Sourcegraph Cody
  • Cursor
  • Visual Studio Code
  • LibreChat
  • Various CLI and browser-based clients

(Icons and links for specific clients are commonly shown on the individual server/project pages.)


Server Implementations (Categories)

  • 📂 File Systems
  • 📦 Sandbox & Virtualization
  • 🔄 Version Control
  • ☁️ Cloud Storage
  • 🗄️ Databases
  • 💬 Communication
  • 📈 Monitoring
  • 🔍 Search & Web
  • 🗺️ Location Services
  • 🎯 Marketing
  • 📝 Note Taking
  • ⚡ Cloud Platforms
  • ⚙️ Workflow Automation
  • 🤖 System Automation
  • 📱 Social Media
  • 🎮 Gaming
  • 💹 Finance
  • 🧬 Research & Data
  • 🤝 AI Services
  • 💻 Development Tools
  • 📊 Data Visualization
  • 🆔 Identity
  • 🔗 Aggregators
  • 💬 Language & Translation
  • 🔒 Security
  • 🔌 IoT
  • 🧑‍🎨 Art & Literature
  • 🛒 E-Commerce
  • 📦 Data Platforms
  • 🤖 Robotics & Physical AI

Legend:

  • ⭐ Official protocol implementation
  • 1,2,3,… Implementation ordering when multiple exist

Reference Servers

These are example/reference servers and core SDK examples demonstrating MCP features.


Official Servers

Official integrations are maintained by companies building production-ready MCP servers for their platforms. (Marked with ⭐ when present)

(For a full list of official servers and vendor-maintained implementations, see the “Official Servers” and “Reference Servers” in this document and the linked repos.)


Tools & Utilities

Helpful utilities to discover, install, manage, and work with MCP servers.

Server Managers:

Other utilities:


Category: File Systems (📂)

Provides access to local or remote file systems with configurable permissions.


Category: Sandbox & Virtualization (📦)

Secure sandbox environments for code execution.


Category: Version Control (🔄)

Git and version control related MCP servers.


Category: Cloud Storage (☁️)

Access to cloud storage platforms.


Category: Databases (🗄️)

Database access with schema inspection and query capabilities.


Category: Communication (💬)

Integration with chat and messaging platforms.


Category: Monitoring (📈)

Access observability and monitoring systems.


Web fetching, scraping, and search.


Category: Location Services (🗺️)

Mapping and geolocation.


Category: Marketing (🎯)

Marketing and analytics tools.


Category: Note Taking (📝)

Personal knowledge and notes integrations.


Category: Cloud Platforms (⚡)

Cloud vendors and orchestration.


Category: Workflow Automation (⚙️)

Automation platforms and workflow tools.


Category: System Automation (🤖)

Shell, OS, and task automation.


Category: Social Media (📱)

Social platforms integration.


Category: Gaming (🎮)

Game engines and tooling.


Category: Finance (💹)

Payments, market data, and finance tools.


Category: Research & Data (🧬)

Papers, datasets, and domain data.


Category: AI Services (🤝)

AI model & ML service integrations.


Category: Development Tools (💻)

Developer-focused MCP servers and tools.


Category: Data Visualization (📊)

Charting and diagram tools.


Category: Identity (🆔)

Identity and access management.


Category: Aggregators (🔗)

Single MCP endpoints that expose many integrations.


Category: Language & Translation (💬)

Translation and language services.


Category: Security (🔒)

Security-focused servers and scanning tools.


Category: IoT (🔌)

MCP servers for device and IoT integration.


Category: Art & Literature (🧑‍🎨)

Books, libraries, and creative tools.


Category: E-Commerce (🛒)

Commerce and marketplace integrations.


Category: Data Platforms (📦)

Orchestration and data pipeline platforms.


Category: Robotics & Physical AI (🤖)

Robotics and device control.


Community Servers

A broad collection of community-maintained MCP servers (selected highlights — many more are available in the ecosystem):

(For the exhaustive long list of community servers and links, refer to the aggregated listings in community and official sections across the MCP ecosystem. This README collects and organizes the major categories and many example projects; the community maintains a rapidly growing set of servers — check the linked repos for the latest.)


Clients

Clients and UI tools that consume MCP servers:


Frameworks

Frameworks and scaffolding for building MCP servers:


Notes & Recommendations

  • Always run untrusted or community MCP servers in an isolated environment (container or VM) and restrict access to sensitive resources.
  • Prefer official vendor-maintained servers (marked with ⭐) for production use.
  • Check each server repo for documentation about transports (stdio, SSE, HTTP), authentication, and example clients.
  • This ecosystem evolves rapidly — many new servers, clients, and frameworks are added frequently. If you maintain a server, ensure the repo has clear installation and security instructions.
关于

A curated list of Model Context Protocol (MCP) servers

73.0 KB
邀请码
    Gitlink(确实开源)
  • 加入我们
  • 官网邮箱:gitlink@ccf.org.cn
  • QQ群
  • QQ群
  • 公众号
  • 公众号

©Copyright 2023 CCF 开源发展委员会
Powered by Trustie& IntelliDE 京ICP备13000930号