Apisix 模型上下文协议 (mcp) 服务器

什麼是 APISIX 模型上下文協議 (MCP)？

APISIX 模型上下文協議 (MCP) 是一個伺服器，旨在將大型語言模型 (LLMs) 與 APISIX 管理 API 連接起來。這種整合使開發者能夠在其應用中利用 LLM 的能力，增強功能並實現更複雜的互動。

APISIX MCP 的特點

• 無縫整合：APISIX MCP 提供了一種簡單的方法來將 LLM 與 APISIX 管理 API 連接，方便輕鬆訪問先進的語言處理能力。
• 公共庫：該項目是開源的，並可在 GitHub 上獲得，允許開發者貢獻和自定義解決方案以滿足其需求。
• Apache-2.0 許可證：MCP 採用 Apache-2.0 許可證，確保可以自由使用和修改。
• 社區支持：隨著 GitHub 上越來越多的星標和分支，APISIX MCP 周圍的社區活躍，提供支持和增強功能。

如何使用 APISIX MCP

1. 安裝：首先從 GitHub 克隆該庫。使用以下命令：

   git clone https://github.com/api7/apisix-mcp.git
   

2. 配置：設置必要的配置以將您的 LLM 與 APISIX 管理 API 連接。這可能涉及指定 API 端點和身份驗證詳細信息。
3. 部署：在您的環境中部署 MCP 伺服器。確保它對將利用 LLM 能力的應用可訪問。
4. 整合：使用提供的 API 端點與 LLM 互動。這可以包括發送請求以進行文本生成、分析或其他語言處理任務。

常見問題解答

使用 APISIX MCP 的先決條件是什麼？

要使用 APISIX MCP，您應該對 API 有基本了解，並熟悉 Git 以克隆該庫。此外，了解您計劃用於整合的編程語言會有所幫助。

我可以為 APISIX MCP 項目做貢獻嗎？

可以！該項目是開源的，歡迎貢獻。您可以在 GitHub 倉庫上提交問題、功能請求或拉取請求。

有可用的文檔嗎？

有，詳細的文檔通常在倉庫的 README 文件和其他 Markdown 文件中提供。您還可以在問題部分找到社區討論和示例。

我該如何報告錯誤或請求功能？

您可以通過在 GitHub 倉庫上打開問題來報告錯誤或請求功能。請確保提供清晰的描述和任何相關細節，以幫助維護者有效地處理您的請求。

APISIX Model Context Protocol (MCP) Server

APISIX Model Context Protocol (MCP) server is used to bridge large language models (LLMs) with the APISIX Admin API. It aims to enable natural language-based interaction for viewing and managing resources in APISIX through MCP-compatible AI clients.

https://github.com/user-attachments/assets/081e878c-225e-4ff8-a9c5-5813f4784cfe

Support Operations

Common Operations

• get_resource: Retrieve resources by type (routes, services, upstreams, etc.)
• delete_resource: Remove resources by ID
• send_request_to_gateway: Send a request or multiple requests to the APISIX gateway

API Resources Operations

• create_route/update_route/delete_route: Manage routes
• create_service/update_service/delete_service: Manage services
• create_upstream/update_upstream/delete_upstream: Manage upstream
• create_ssl/update_ssl/delete_ssl: Manage SSL certificates
• create_or_update_proto: Manage protobuf definitions
• create_or_update_stream_route: Manage stream routes

Plugin Operations

• get_all_plugin_names: Get all available plugin names
• get_plugin_info/get_plugins_by_type/get_plugin_schema: Retrieve plugins configuration
• create_plugin_config/update_plugin_config: Manage plugin configurations
• create_global_rule/update_global_rule: Manage plugin global rules
• get_plugin_metadata/create_or_update_plugin_metadata/delete_plugin_metadata: Manage plugin metadata

Security Configuration

• get_secret_by_id/create_secret/update_secret: Manage secrets
• create_or_update_consumer/delete_consumer: Manage consumers
• get_credential/create_or_update_credential/delete_credential/: Manage consumer credentials
• create_consumer_group/delete_consumer_group: Manage consumer groups

Configuration in AI client

Prerequisite

Follow the APISIX Getting Started guide to set up and run APISIX.

Installing via Smithery

To install APISIX Model Context Protocol Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @api7/apisix-mcp --client claude

Using npm

Configure your AI client (Cursor, Claude, Copilot, etc.) with following settings:

{
  "mcpServers": {
    "apisix-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "apisix-mcp"
      ],
      "env": {
        "APISIX_SERVER_HOST": "your-apisix-server-host",
        "APISIX_SERVER_PORT": "your-apisix-server-port",
        "APISIX_ADMIN_API_PORT": "your-apisix-admin-api-port",
        "APISIX_ADMIN_API_PREFIX": "your-apisix-admin-api-prefix",
        "APISIX_ADMIN_KEY": "your-apisix-api-key"
      }
    }
  }
}

Using source code

First clone the apisix-mcp repository:

git clone https://github.com/api7/apisix-mcp.git
cd apisix-mcp

Install the dependencies and build the project:

pnpm install
pnpm build

Configure your AI client (Cursor, Claude, Copilot, etc.) with following settings:

{
  "mcpServers": {
    "apisix-mcp": {
      "command": "node",
      "args": [
        "your-apisix-mcp-path/dist/index.js"
      ],
      "env": {
        "APISIX_SERVER_HOST": "your-apisix-server-host",
        "APISIX_SERVER_PORT": "your-apisix-server-port",
        "APISIX_ADMIN_API_PORT": "your-apisix-admin-api-port",
        "APISIX_ADMIN_API_PREFIX": "your-apisix-admin-api-prefix",
        "APISIX_ADMIN_KEY": "your-apisix-api-key"
      }
    }
  }
}

Environment Variables

Variable	Description	Default Value
APISIX_SERVER_HOST	Host that have access to your APISIX server	http://127.0.0.1
APISIX_SERVER_PORT	APISIX server port	9080
APISIX_ADMIN_API_PORT	Admin API port	9180
APISIX_ADMIN_API_PREFIX	Admin API prefix	/apisix/admin
APISIX_ADMIN_KEY	Admin API authentication key	edd1c9f034335f136f87ad84b625c8f1

To view or modify Admin API configurations in APISIX, refer to the Admin API documentation.

Resources

Open MCP Marketplace API Support

|GitHub|Doc|MCP Marketplace

• Allow AI App/Agent/LLM to find this MCP Server via common python/typescript API, search and explore relevant servers and tools

Example: Search Server and Tools

    import anthropic
    import mcp_marketplace as mcpm

    result_q = mcpm.search(query="apisix mcp", mode="list", page_id=0, count_per_page=100, config_name="deepnlp") # search server by category choose various endpoint
    result_id = mcpm.search(id="api7/apisix-mcp", mode="list", page_id=0, count_per_page=100, config_name="deepnlp")      # search server by id choose various endpoint 
    tools = mcpm.list_tools(id="api7/apisix-mcp", config_name="deepnlp_tool")

    # Call Claude to Choose Tools Function Calls 
    client = anthropic.Anthropic()
    response = client.messages.create(model="claude-3-7-sonnet-20250219", max_tokens=1024, tools=tools, messages=[])