SERP Maven — Claude Code MCP server: what it does, how to install
The SERP Maven MCP server for Claude Code connects AI agents to live Google search results through a real browser and residential proxies. It runs search queries from the IDE.
MIT ★ 129 updated 2026-11-16
claude mcp add --env NODEMAVEN_LOGIN=<NODEMAVEN_LOGIN> --env NODEMAVEN_PASSWORD=<NODEMAVEN_PASSWORD> --env SERPMAVEN_PROXY=<SERPMAVEN_PROXY> --transport stdio serp-maven -- uvx serpmavenWhat SERP Maven does
The tool extracts search results into structured JSON covering organic links, ads, and local listings. Under the hood, it relies on a real Google Chrome browser managed by Patchright with session cookies to bypass checks. Traffic routes through sticky residential proxies equipped with poisoned results protection.
The setup requires Python 3.10 or newer and a residential proxy with sticky sessions. You need to provide proxy credentials via environment variables before launching.
What it helps with
- fetch live Google search results as JSON
- monitor keyword rankings and SEO metrics
- gather competitor data from search pages
- feed search queries directly to AI agents
Example prompts for the agent
- Search Google for recent articles about python mcp servers
- Get organic search results for the keyword seo tools
- Query top Google results for devops automation
How to install SERP Maven
Platform CLI
claude mcp add --env NODEMAVEN_LOGIN=<NODEMAVEN_LOGIN> --env NODEMAVEN_PASSWORD=<NODEMAVEN_PASSWORD> --env SERPMAVEN_PROXY=<SERPMAVEN_PROXY> --transport stdio serp-maven -- uvx serpmavenReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from serpmaven <command>
Platform CLI
codex mcp add serp-maven --env NODEMAVEN_LOGIN=<NODEMAVEN_LOGIN> --env NODEMAVEN_PASSWORD=<NODEMAVEN_PASSWORD> --env SERPMAVEN_PROXY=<SERPMAVEN_PROXY> -- uvx serpmavenReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from serpmaven <command>
Config file
{
"mcpServers": {
"serp-maven": {
"command": "uvx",
"args": [
"serpmaven"
],
"env": {
"NODEMAVEN_LOGIN": "<NODEMAVEN_LOGIN>",
"NODEMAVEN_PASSWORD": "<NODEMAVEN_PASSWORD>",
"SERPMAVEN_PROXY": "<SERPMAVEN_PROXY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from serpmaven <command>
Config file
{
"servers": {
"serp-maven": {
"type": "stdio",
"command": "uvx",
"args": [
"serpmaven"
],
"env": {
"NODEMAVEN_LOGIN": "<NODEMAVEN_LOGIN>",
"NODEMAVEN_PASSWORD": "<NODEMAVEN_PASSWORD>",
"SERPMAVEN_PROXY": "<SERPMAVEN_PROXY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from serpmaven <command>
Platform CLI
gemini mcp add -e NODEMAVEN_LOGIN=<NODEMAVEN_LOGIN> -e NODEMAVEN_PASSWORD=<NODEMAVEN_PASSWORD> -e SERPMAVEN_PROXY=<SERPMAVEN_PROXY> serp-maven uvx serpmavenReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from serpmaven <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about SERP Maven
How to install SERP Maven in Claude Code?
Run claude mcp add serpmaven -e NODEMAVEN_PASSWORD=<NODEMAVEN_PASSWORD> -e SERPMAVEN_PROXY=<SERPMAVEN_PROXY> -- uvx serpmaven or `claude mcp add --env NODEMAVEN_LOGIN=<NODEMAVEN_LOGIN> --env NODEMAVEN_PASSWORD=<NODEMAVEN_PASSWORD> --env SERPMAVEN_PROXY=<SERPMAVEN_PROXY> --transport stdio serp-maven -- uvx serpmaven`.
What does SERP Maven do?
It gives AI agents access to live Google search results through a real automated browser and proxy setup.
What is needed to run SERP Maven?
You need Python 3.10 or newer and a residential proxy that supports sticky sessions.