Schema | google-surf-mcp

google-surf-mcp

Describes the environment variables required to run the server.

Name	Required	Description
`SURF_TZ`	No	Timezone for the browser (e.g. America/New_York, default: system timezone)
`CHROME_PATH`	No	Absolute path to Chrome binary (auto-detected if not set)
`SURF_LOCALE`	No	Browser locale (default: en-US)
`SURF_HEADLESS`	No	Set to 'false' to run Chrome visibly (default: 'true')
`SURF_PROFILE_ROOT`	No	Directory where the warm Chrome profile lives (default: ~/.google-surf-mcp)
`SURF_IDLE_CLOSE_MS`	No	Idle milliseconds before closing browser contexts (default: '30000')

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
searchB	Single Google search. Returns title/url/snippet per result. ~2s/query (first call ~4s, includes setup). On CAPTCHA, a visible Chrome window opens for the human to solve, then the call retries.
search_parallelA	Run multiple Google searches in parallel (pool of 4). Returns title/url/snippet per result. First call adds 5–10s setup.
extractA	Fetch a URL and return clean article markdown. Uses Mozilla Readability with a text fallback. Best-effort: failures return { error } instead of throwing. Private/loopback addresses blocked unless SURF_ALLOW_PRIVATE=true.
search_extractA	Google search + parallel content extraction. Returns SERP results enriched with article markdown. Slower than search (extra ~2–5s) but gives you actual page content, not just snippets. Per-page failures are isolated (returned as { error } in that result).

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HarimxChoi/google-surf-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server