Google Surf MCP server

by HarimxChoi·io.github.HarimxChoi/google-surf-mcp·v1.1.3

No reviews yet

Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.

B83/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B83/100

full report

Adoption

Established

290 stars438 downloads/wk

Reviews

Write one

Nobody has reviewed Google Surf yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Google Surf tools (7)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

extract
SECONDARY KNOWN-URL CONTENT EXTRACTION TOOL. Use only when the exact public URL is already known and no new web discovery is required. If sources still need to be found, use search or search_parallel with extract_mode instead.
health
MCP server status: cascade mode + transitions, rate-limiter usage, cache size, config.
project_memory
PROJECT MEMORY MANAGEMENT.
project_memory_search
LOCAL PROJECT KNOWLEDGE SEARCH ONLY.
scholar_search
Use only for paper metadata such as authors, venue, year, versions, and citation counts.
search
PRIMARY SINGLE-QUERY LIVE DISCOVERY AND CONTENT INGESTION TOOL. ALWAYS PERFORMS LIVE WEB SEARCH.
search_parallel
PRIMARY MULTI-QUERY LIVE DISCOVERY AND CONTENT INGESTION TOOL. ALWAYS PERFORMS MULTIPLE LIVE WEB SEARCHES.

Public scan report

scanner v0.1.8 · 2026-09-19 · same rubric, same numbers if you re-run it

no findings

Code scan79 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 9 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Grade history

2026-09-19restoreC → Bscore 83

Install directly

Runs npx -y google-surf-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add google-surf-mcp -- npx -y google-surf-mcp

Add to Cursor

Google Surf: common questions

Is Google Surf MCP server safe?: Mostly: it is graded B (83/100). Read the Google Surf safety report
How do I install Google Surf?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Google Surf need an API key?: Yes. The registry entry asks for SEARCH_API, GITHUB_TOKEN, ANTHROPIC_API_KEY, ORCAROUTER_API_KEY.
Is Google Surf maintained?: The last commit was 9 days ago (2026-09-10). The latest release is v1.1.3.
What can I use instead of Google Surf?: Servers from other publishers that do the same job: rag-rat MCP server, Sanity MCP server and Agent-Native Slides MCP server. Compare all Google Surf alternatives.

Alternatives to Google Surf

Same job from other publishers: the closest match first, then the best rated.

All Google Surf alternatives →

rag-rat
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
not reviewed
Growing
B
Sanity
Direct access to your Sanity projects (content, datasets, releases, schemas) and agent rules
not reviewed
Growing
A
Agent-Native Slides
Agent-Native Google Slides - generate and edit React presentations
not reviewed
Established
A
Local Rag
Easy-to-setup local RAG server with minimal configuration
not reviewed
Established
A
ContextStream MCP Server
Project memory, semantic code search, and grounded agent context.
not reviewed
Established
A

Google Surf vs rag-rat Google Surf vs Sanity Google Surf vs Agent-Native Slides

Run it through the gateway

Local package. It runs on your machine, not through the gateway.

Rating: —
Safety grade: B · 83/100
Stars: 290
Downloads/wk: 438
Price: Free
Licence: MIT
Transport: Local · npm
Version: 1.1.3
Category: AI and agents
Last release: 2026-09-10

Credentials it needs

SEARCH_APIsecretSearchApi API key. Required only for SearchApi primary or fallback modes.
SURF_SEARCH_PROVIDERProvider for search and search_parallel: browser, searchapi, or fallback. Defaults to browser.
SURF_SCHOLAR_PROVIDERProvider for scholar_search: browser, searchapi, or fallback. Defaults to browser.
SURF_BROWSER_ENGINEBrowser engine: auto, native, or playwright. Auto uses one hidden native Chrome broker shared across local MCP sessions.
CHROME_PATHAbsolute path to the Chrome binary. Auto-detected on Windows/macOS/Linux when omitted.
SURF_PROFILE_ROOTDirectory for the warm Chrome profile. Defaults to ~/.google-surf-mcp.
SURF_RESEARCHEnable local project memory and hybrid retrieval. Defaults to true.
SURF_RETRIEVAL_MODEShared route for search and search_parallel: live or hybrid. Defaults to hybrid.
SURF_RESEARCH_ROOTEmbedded SurrealDB data directory. Defaults to <profile>/research.
SURF_RESEARCH_VECTOR_MODELLocal model for HNSW retrieval and shared reranking. Defaults to Xenova/multilingual-e5-small; use off to disable.
SURF_RESEARCH_VECTOR_LOW_MEMORYDisable ONNX CPU memory arena and memory pattern. Defaults to true.
SURF_RESEARCH_VECTOR_THREADSONNX intra-op thread count from 1 to 16. Defaults to 4.
SURF_RESEARCH_REPO_AUTOSparse-index at most one eligible small GitHub repository per search call. Defaults to true.
SURF_RESEARCH_REPO_AUTO_MAX_MBMaximum searchable repository source-text size in MB. Assets are excluded. Defaults to 20.
SURF_RESEARCH_REPO_AUTO_MAX_FILESMaximum repository source file count for automatic indexing. Defaults to 2000.
SURF_RESEARCH_BROKER_IDLE_MSShared research broker idle lifetime in milliseconds. Defaults to 60000.
SURF_RESEARCH_READ_CONCURRENCYMaximum concurrent research broker reads. Defaults to 4.
SURF_RESEARCH_QUERY_TIMEOUT_MSTimeout per embedded SurrealDB query in milliseconds. Defaults to 120000; timed-out retrieval lanes are reported as partial.
GITHUB_TOKENsecretOptional token that raises GitHub API limits for repository inspection.
SURF_LOCALEBrowser locale, e.g. en-US.
SURF_TZIANA timezone, e.g. America/New_York. Defaults to system timezone.
SURF_HEADLESSControls Playwright extraction, compatibility, and recovery paths. Native search hides normal system Chrome and shows it only for CAPTCHA recovery.
SURF_IDLE_CLOSE_MSIdle ms before closing the sequential ctx and pool. 0 disables idle auto-close. Defaults to 30000.
SURF_ALLOW_PRIVATESet 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_HEALEnable the optional workflow-only LLM selector repair path. Defaults to false.
SURF_LLM_PROVIDERLLM selector repair provider: anthropic or orcarouter. Defaults to anthropic.
SURF_LLM_MODELOptional model override. OrcaRouter defaults to orcarouter/auto.
ANTHROPIC_API_KEYsecretAnthropic API key for optional LLM-assisted selector repair.
ORCAROUTER_API_KEYsecretOrcaRouter API key for optional LLM-assisted selector repair.

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/harimxchoi-google-surf-mcp.svg)](https://mcp.market/server/harimxchoi-google-surf-mcp)

How the badge works