Google Search MCP

A Playwright-based MCP server that performs Google searches by automating a local browser. Extracts search results, captures screenshots, and retrieves raw HTML without requiring any API keys. Includes anti-bot fingerprinting and browser state persistence.

Evaluated Mar 07, 2026 (0d ago) vunknown
Homepage ↗ Repo ↗ Other google-search playwright mcp-server web-scraping typescript browser-automation search
⚙ Agent Friendliness
52
/ 100
Can an agent use this?
🔒 Security
62
/ 100
Is it safe for agents?
⚡ Reliability
52
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
50
Error Messages
35
Auth Simplicity
75
Rate Limits
50

🔒 Security

TLS Enforcement
80
Auth Strength
60
Scope Granularity
50
Dep. Hygiene
60
Secret Handling
58

Community/specialized tool. Apply standard security practices for category. Review documentation for specific security requirements.

⚡ Reliability

Uptime/SLA
55
Version Stability
55
Breaking Changes
50
Error Recovery
50
AF Security Reliability

Best When

You need occasional local Google searches from an AI agent without API costs, for learning or research purposes, and accept the fragility of scraping.

Avoid When

You need reliable production search, high volume, or compliance with Google's Terms of Service. Use official Google Search API or SerpAPI instead.

Use Cases

  • Giving AI agents web search capability without API keys or paid search APIs
  • Extracting Google search results with raw HTML for analysis
  • Research automation where an agent needs to search the web locally

Not For

  • High-volume or production search workloads (risks IP blocking by Google)
  • Commercial use at scale (likely violates Google Terms of Service)
  • Reliable, consistent search results (Google layout changes can break parsing)
  • Environments where running a full browser is impractical

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication required. The tool scrapes Google directly by automating a browser, bypassing the need for API keys. Browser state files contain cookies and should be kept confidential.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

No license explicitly stated in repo. Free to use but Google ToS compliance is the user's responsibility. Explicitly noted as for 'learning and research purposes only'.

Agent Metadata

Pagination
none
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • Google can block your IP with frequent requests - no built-in rate limiting
  • HTML parsing breaks when Google changes page layout
  • Requires downloading full Playwright browser binaries (100+ MB)
  • Browser state files contain sensitive cookies - security risk if shared
  • Likely violates Google Terms of Service for automated access
  • No license declared in repository
  • Windows may require admin privileges for browser installation
  • 60-second default timeout means slow responses for agents

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Google Search MCP.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-07.

6347
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered