google-surf-mcp
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
Open the source (opens github.com) https://github.com/harimxchoi/google-surf-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: ANTHROPIC_API_KEY, GITHUB_TOKEN, ORCAROUTER_API_KEY, SEARCH_API. Use a key with the least access you can.
What it is
MCP servers from io.github.HarimxChoi.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
google-surf-mcp@1.1.6
From the server's entry in the official MCP Registry
Settings it asks for
SEARCH_APIsecret · SearchApi API key. Required only for SearchApi primary or fallback modes.SURF_SEARCH_PROVIDER· Provider for search and search_parallel: browser, searchapi, or fallback. Defaults to browser.SURF_SCHOLAR_PROVIDER· Provider for scholar_search: browser, searchapi, or fallback. Defaults to browser.SURF_BROWSER_ENGINE· Browser engine: auto, native, or playwright. Auto uses one hidden native Chrome broker shared across local MCP sessions.CHROME_PATH· Absolute path to the Chrome binary. Auto-detected on Windows/macOS/Linux when omitted.SURF_PROFILE_ROOT· Directory for the warm Chrome profile. Defaults to ~/.google-surf-mcp.SURF_RESEARCH· Enable Google Surf Auto Ontology: local project memory, evidence capture, and hybrid retrieval. Defaults to true. The SURF_RESEARCH setting name is unchanged.SURF_RETRIEVAL_MODE· Shared route for search and search_parallel: live or hybrid. Defaults to hybrid.SURF_RESEARCH_ROOT· Embedded SurrealDB data directory. Defaults to <profile>/research.SURF_RESEARCH_VECTOR_MODEL· Local model for HNSW retrieval and shared reranking. Defaults to Xenova/multilingual-e5-small; use off to disable.SURF_RESEARCH_VECTOR_LOW_MEMORY· Disable ONNX CPU memory arena and memory pattern. Defaults to true.SURF_RESEARCH_VECTOR_THREADS· ONNX intra-op thread count from 1 to 16. Defaults to 4.
Related
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.
-
Playwright MCP
MCP serversLets an agent drive a real browser: open pages, click, fill in forms and read what's on screen.
claude mcp add playwright npx @playwright/mcp@latest