Sponsored by Deepsite.site

mcp-server-indexnow

Created By
zizzfizzix8 months ago
A Model Context Protocol (MCP) server allowing URL indexing requests via the IndexNow protocol. This server acts as a bridge, enabling MCP-compatible clients (like IDEs or AI assistants) to submit URLs to search engines using the IndexNow protocol for potentially faster content discovery and indexing.
Content

mcp-server-indexnow

A Model Context Protocol (MCP) server allowing URL indexing requests via the IndexNow protocol.

This server acts as a bridge, enabling MCP-compatible clients (like IDEs or AI assistants) to submit URLs to search engines using the IndexNow protocol for potentially faster content discovery and indexing.

What is IndexNow?

IndexNow is a simple protocol that allows websites to easily notify search engines whenever their website content is created, updated, or deleted. Submitting URLs via IndexNow informs participating search engines (like Bing, Yandex, Seznam.cz, Naver, Yep) to prioritize crawling these URLs, potentially speeding up the reflection of changes in search results.

What is MCP?

The Model Context Protocol (MCP) is a standard for connecting language models (LLMs) and AI assistants to various tools, data sources, and capabilities through dedicated servers. This server implements MCP to expose IndexNow functionality as a tool.

Features

  • Provides an MCP tool to submit single or multiple URLs to the IndexNow API.
  • Facilitates interaction with the IndexNow protocol through MCP clients.
  • Requires minimal configuration once the IndexNow key is set up on your host.

Installation

When using uvx no specific installation is needed. We will use it to directly run mcp_server_indexnow from the client app.

Add to Claude desktop with uvx

In your Claude config specify:

"mcpServers": {
  "mcp_server_indexnow": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/zizzfizzix/mcp-server-indexnow",
      "mcp_server_indexnow"
    ]
  }
}

Add to Zed with uvx

In your Zed settings.json add:

"context_servers": [
  "mcp_server_indexnow": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/zizzfizzix/mcp-server-indexnow",
      "mcp_server_indexnow"
    ]
  }
],

Using make

Alternatively you can install mcp_server_indexnow using make:

make install

Add to Claude desktop with make

In your Claude config specify:

"mcpServers": {
  "mcp_server_indexnow": {
    "command": "/path/to/mcp-server-indexnow/.venv/bin/python",
    "args": ["/path/to/mcp-server-indexnow/mcp_server_indexnow/main.py"]
  }
}

Add to Zed with make

In your Zed settings.json add:

"context_servers": {
  "mcp_server_indexnow": {
    "command": "/path/to/mcp-server-indexnow/.venv/bin/python",
    "args": ["/path/to/mcp-server-indexnow/mcp_server_indexnow/main.py"]
  }
}

Usage

After you've successfully added this MCP server to your assistant app follow the next steps below.

1. IndexNow Key Setup (Required)

Before using this server, you must set up an IndexNow key for your website host. This involves generating a key and placing a specific text file ({your-key}.txt) on your web server. This process verifies your ownership of the host to IndexNow.

  • Follow the official IndexNow instructions: Verifying ownership via the key
  • The key itself will be needed when you invoke the URL submission tool provided by this server. Keep it secure.

2. Environment Variables (Optional)

This server supports the following environment variables for configuration:

  • INDEXNOW_SECRET_KEY: If you set this environment variable to your IndexNow key, the server will use it by default when submitting URLs. This way your AI assistant won't know it. You can still override it by providing the key argument when invoking the tool e.g.:
"mcpServers": {
  "mcp_server_indexnow": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/zizzfizzix/mcp-server-indexnow",
      "mcp_server_indexnow"
    ],
    "env": {
      "INDEXNOW_SECRET_KEY": "https://example.com/2134131231.txt"
    }
  }
}
  • INDEXNOW_API_BASE: Allows you to specify a different IndexNow API endpoint. Defaults to https://api.indexnow.org/indexnow, full list at indexnow.com. You typically only need this if you care about network latency or a specific participating search engine - they share submitted events with each other in the background but there reasonably might be a delay.
"mcpServers": {
  "mcp_server_indexnow": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/zizzfizzix/mcp-server-indexnow",
      "mcp_server_indexnow"
    ],
    "env": {
      "INDEXNOW_API_BASE": "https://www.bing.com/indexnow"
    }
  }
}
  • INDEXNOW_KEY_LOCATION: Optional. Full URL to your key file if not hosted at the root (/keyfilename.txt). Use this if you followed Option 2 from the IndexNow documentation.
"mcpServers": {
  "mcp_server_indexnow": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/zizzfizzix/mcp-server-indexnow",
      "mcp_server_indexnow"
    ],
    "env": {
      "INDEXNOW_KEY_LOCATION": "https://example.com/some/path/myIndexNowKey63638.txt"
    }
  }
}

Examples

Interact with your MCP client (e.g., AI Assistant) to invoke the tool. The exact command might depend on the client, but conceptually:

Assistant, please use the IndexNow server to submit the URL https://your-website.com/updated-page with the key 'your-indexnow-key'.

Or for multiple URLs:

Assistant, please use the IndexNow server to submit the following URLs with the key 'your-indexnow-key':

  • https://your-website.com/new-article-1
  • https://your-website.com/new-article-2
  • https://your-website.com/deleted-page

Refer to your specific MCP client's documentation on how to invoke server tools. This server will then make the appropriate request to the IndexNow API endpoint, by default https://api.indexnow.org/indexnow.

Development

For development, you can use the following commands:

# Install dependencies
make install

# Start the server
make start

# Run tests
make test

# Run linting
make lint

# Format code
make format

Debugging

You can use the MCP inspector to debug the server.

make mcp_inspector

Creating from Template

This MCP server was created from a cookiecutter template. To create a similar one, run:

uvx cookiecutter gh:zizzfizzix/python-base-mcp-server

License

mcp-server-indexnow is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Playwright McpPlaywright MCP server
ChatWiseThe second fastest AI chatbot™
Amap Maps高德地图官方 MCP Server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
WindsurfThe new purpose-built IDE to harness magic
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
CursorThe AI Code Editor
Serper MCP ServerA Serper MCP Server
DeepChatYour AI Partner on Desktop
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Tavily Mcp