Do you maintain this server? Claim this listing to add a logo or screenshot and to correct or extend it. Free, and a person checks every claim.
What it does
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
Description as published by the publisher in the official MCP Registry, read 10 Oct 2026. Not written or verified by Few Servers.
Facts
| Registry name | io.github.HarimxChoi/google-surf-mcp |
|---|---|
| Publisher | GitHub account HarimxChoi Namespace verified by the registry through the publisher's GitHub account. |
| Category | Developer tools sorted by our keyword rules |
| Transport | local package (npm) |
| Version | 1.1.3 |
| This version published | 10 Sep 2026 |
| GitHub stars | 291 on harimxchoi/google-surf-mcp read from GitHub on 12 Oct 2026. GitHub's count, not a rating by us. |
| Last seen | 10 Oct 2026, in our crawl of the official MCP Registry |
| Tested by Few Servers | No |
Install
- npm package, as published:
google-surf-mcp· version 1.1.3 · transport stdio
Standard run command for npm packages. The registry publishes the package name, not a command; check the repository for required arguments.npx -y google-surf-mcp
Install details read from the registry record on 12 Oct 2026. We have not run this server.
Keys and settings
The registry record declares a secret value (a key or token) that is not marked required. Declared by the publisher:
SEARCH_API(environment variable, secret, not marked required): SearchApi API key. Required only for SearchApi primary or fallback modes.SURF_SEARCH_PROVIDER(environment variable, not marked required): Provider for search and search_parallel: browser, searchapi, or fallback. Defaults to browser.SURF_SCHOLAR_PROVIDER(environment variable, not marked required): Provider for scholar_search: browser, searchapi, or fallback. Defaults to browser.SURF_BROWSER_ENGINE(environment variable, not marked required): Browser engine: auto, native, or playwright. Auto uses one hidden native Chrome broker shared across local MCP sessions.CHROME_PATH(environment variable, not marked required): Absolute path to the Chrome binary. Auto-detected on Windows/macOS/Linux when omitted.SURF_PROFILE_ROOT(environment variable, not marked required): Directory for the warm Chrome profile. Defaults to ~/.google-surf-mcp.SURF_RESEARCH(environment variable, not marked required): Enable local project memory and hybrid retrieval. Defaults to true.SURF_RETRIEVAL_MODE(environment variable, not marked required): Shared route for search and search_parallel: live or hybrid. Defaults to hybrid.SURF_RESEARCH_ROOT(environment variable, not marked required): Embedded SurrealDB data directory. Defaults to <profile>/research.SURF_RESEARCH_VECTOR_MODEL(environment variable, not marked required): Local model for HNSW retrieval and shared reranking. Defaults to Xenova/multilingual-e5-small; use off to disable.SURF_RESEARCH_VECTOR_LOW_MEMORY(environment variable, not marked required): Disable ONNX CPU memory arena and memory pattern. Defaults to true.SURF_RESEARCH_VECTOR_THREADS(environment variable, not marked required): ONNX intra-op thread count from 1 to 16. Defaults to 4.SURF_RESEARCH_REPO_AUTO(environment variable, not marked required): Sparse-index at most one eligible small GitHub repository per search call. Defaults to true.SURF_RESEARCH_REPO_AUTO_MAX_MB(environment variable, not marked required): Maximum searchable repository source-text size in MB. Assets are excluded. Defaults to 20.SURF_RESEARCH_REPO_AUTO_MAX_FILES(environment variable, not marked required): Maximum repository source file count for automatic indexing. Defaults to 2000.SURF_RESEARCH_BROKER_IDLE_MS(environment variable, not marked required): Shared research broker idle lifetime in milliseconds. Defaults to 60000.SURF_RESEARCH_READ_CONCURRENCY(environment variable, not marked required): Maximum concurrent research broker reads. Defaults to 4.SURF_RESEARCH_QUERY_TIMEOUT_MS(environment variable, not marked required): Timeout per embedded SurrealDB query in milliseconds. Defaults to 120000; timed-out retrieval lanes are reported as partial.GITHUB_TOKEN(environment variable, secret, not marked required): Optional token that raises GitHub API limits for repository inspection.SURF_LOCALE(environment variable, not marked required): Browser locale, e.g. en-US.SURF_TZ(environment variable, not marked required): IANA timezone, e.g. America/New_York. Defaults to system timezone.SURF_HEADLESS(environment variable, not marked required): Controls Playwright extraction, compatibility, and recovery paths. Native search hides normal system Chrome and shows it only for CAPTCHA recovery.SURF_IDLE_CLOSE_MS(environment variable, not marked required): Idle ms before closing the sequential ctx and pool. 0 disables idle auto-close. Defaults to 30000.SURF_ALLOW_PRIVATE(environment variable, not marked required): Set to 'true' to allow extract on private/loopback addresses (localhost, 10.x, 192.168.x, 169.254.x, etc). Default blocks them as an SSRF guard.SURF_LLM_HEAL(environment variable, not marked required): Enable the optional workflow-only LLM selector repair path. Defaults to false.SURF_LLM_PROVIDER(environment variable, not marked required): LLM selector repair provider: anthropic or orcarouter. Defaults to anthropic.SURF_LLM_MODEL(environment variable, not marked required): Optional model override. OrcaRouter defaults to orcarouter/auto.ANTHROPIC_API_KEY(environment variable, secret, not marked required): Anthropic API key for optional LLM-assisted selector repair.ORCAROUTER_API_KEY(environment variable, secret, not marked required): OrcaRouter API key for optional LLM-assisted selector repair.
Links
RepositoryRegistry record (JSON)npm package
Being listed is not a safety check. Read the repository and check what a server asks for before you connect it. How the directory works.
Ratings and reviews
No reviews yet.
Reviews are not open yet. The review inbox is still being set up, so this page cannot take a review today. Nothing is shown here until a real user has written one.