home / mcp / zoomeye mcp server
A Model Context Protocol server that provides network asset information based on query conditions. This server allows LLMs to obtain network asset information and supports querying network asset information by zoomeye dork etc.
Configuration
View docs{
"mcpServers": {
"zoomeye-ai-mcp_zoomeye": {
"command": "uvx",
"args": [
"mcp-server-zoomeye"
],
"env": {
"ZOOMEYE_API_KEY": "YOUR_API_KEY"
}
}
}
}ZoomEye MCP Server lets your AI assistants query ZoomEye to retrieve real-time network asset information based on search queries. It enables you to safely access asset data from ZoomEye through MCP clients, with built-in caching, retries, and robust error handling to support fast, reliable responses for your workflows.
Start the server using one of the supported runtimes, then configure your MCP client to point at the running server. Once set up, you can ask your AI assistant to retrieve network asset information by issuing searches that map to ZoomEye queries. You can request specific fields, control pagination, and choose data types (v4, v6, or web). Use your API key as an environment variable so the server can authenticate to ZoomEye.
Prerequisites: Python 3.10 or higher, Docker, or UVX for running Python packages directly.
# Option 1: Python via pip
pip install mcp-server-zoomeye
# Run with Python
python -m mcp_server_zoomeye# Option 2: Docker
# Pull the latest image
docker pull zoomeyeteam/mcp-server-zoomeye:latest
# Run the container with your ZoomEye API key
docker run -i --rm -e ZOOMEYE_API_KEY=your_api_key_here zoomeyeteam/mcp-server-zoomeye:latest# Option 3: uvx (recommended for quick starts)
# Install uv if you don't have it
# Then run the package directly
uvx pip install mcp-server-zoomeyeSet your ZoomEye API key as an environment variable named ZOOMEYE_API_KEY. This key authenticates requests to the ZoomEye API.
The server requires the following environment variable to access ZoomEye data:
{
"ZOOMEYE_API_KEY": "your_api_key_here"
}Queries ZoomEye for network asset information based on a provided base64-encoded query string, with optional pagination and field selection.