gemini-search-mcp
Provides web search capabilities using Google's AI Mode, allowing agents to search the web and get synthesized answers grounded in real-time results.
Provides an OpenAI-compatible API endpoint for non-MCP clients to use the search functionality, with a base URL of http://localhost:8080/v1.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@gemini-search-mcp search for latest AI regulation news"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
gemini-search-mcp (cn fork)
Free MCP server for web search powered by Google AI Mode (Gemini). Forked from Sophomoresty/gemini-search-mcp with adaptations for non-US IP environments.
What's different from upstream
Aspect | Upstream | This fork |
Target environment | US IP + headed Chrome + persistent profile | Same, plus auto-fallback for headless/non-US |
AI Mode flow | folwr token via | folwr token via |
Strategy | Single (AI Mode only — fails on non-US) | Dual: AI Mode (headed) + organic SERP (headless) |
Login required | No | No |
Related MCP server: gemini-search
Quick start
# 1. Install
pip install -e .
# 2. Prime a persistent Chrome profile (headed, manual CAPTCHA solve if prompted)
python scripts/prime_chrome_v2.py --profile-dir ~/.cache/gemini-search/chrome-profile
# 3. Add to your MCP config (Claude Desktop, Hermes, etc.)MCP server config:
{
"mcpServers": {
"gemini-search": {
"command": "python",
"args": ["-m", "gemini_search_mcp"],
"env": {
"GEMINI_SEARCH_USER_DATA_DIR": "~/.cache/gemini-search/chrome-profile",
"HEADLESS": "0",
"BROWSER_CHANNEL": "chrome"
}
}
}
}Requirements for AI Mode (full quality)
Google AI Mode is gated by 3 things:
headed Chrome window —
--headless=newtriggers/sorry/CAPTCHApersistent profile — fresh profiles get 91KB JS shell instead of 360KB token page
US-region IP — non-US IPs see "AI Mode is not currently available on your device or account"
When all three are met, the engine auto-detects AI Mode availability during _warmup and uses it. When any fails, it falls back to organic SERP extraction (still 5 results with links, just not AI-synthesized).
Headless fallback
Set HEADLESS=1 to run without a visible window. The engine will:
Use the persistent profile (still required)
Detect that AI Mode is blocked (91KB shell, no
data-srtsttoken)Fall back to extracting top 5 organic Google results from the rendered DOM
Answer quality is lower (snippet concat vs Gemini synthesis) but stable and fast.
MCP tools
Tool | Description |
| Search the web and get a synthesized answer grounded in real-time results |
| General question — Gemini Search decides whether to search the web |
Architecture
Agent calls web_search("query")
→ Chrome Runtime.evaluate (CDP via websockets)
→ _warmup: navigate to google.com/search?q=hello (no udm)
→ builds cookie session (NID, AEC, SNID)
→ Probe AI Mode: fetch google.com/search?q=test&udm=50
→ if has data-srtst token → AI Mode enabled
→ if 91KB shell or /sorry/ → organic fallback
→ ask():
[AI Mode path]
→ fetch AI Mode URL (udm=50&aep=1&ntc=1)
→ extract data-srtst, data-xsrf-folwr-token, data-garc, etc.
→ POST to /async/folwr endpoint
→ parse .pTRUV + .n6owBd blocks from HTML
[Organic path]
→ navigate to /search?q=...
→ extract top 5 div.g blocks from rendered DOMFiles
gemini_search/engine.py— Chrome CDP engine, dual strategygemini_search_mcp/— FastMCP server exposingweb_search+asktoolsgemini_search/server.py— OpenAI-compatible API server (gemini-search --port 8080)scripts/prime_chrome_v2.py— headed CAPTCHA priming helperscripts/uc_google_probe.py— undetected-chromedriver probe (for advanced CAPTCHA bypass)scripts/windows_chrome_profile_probe.py— Windows-specific two-phase profile verifiercompare_v2.py— Gemini Search vs Tavily comparison harness (13 queries)generate_report_v2.py— generates markdown report from results JSON
License
MIT (same as upstream)
Available Tools
2 toolsaskARead-only
Ask Google AI Mode any question and get an AI-generated answer.
Similar to web_search but intended for general questions that may or may not require web search. Google AI Mode will automatically decide whether to search the web or answer from its training data.
Args: prompt: Any question or instruction. Google AI Mode will search the web if needed and synthesize an answer.
Returns: AI-generated answer, potentially grounded in web search results.
Inputs: prompt (required). Returns: result
web_searchARead-only
Search the web using Google AI Mode and get a synthesized answer with sources.
Uses Google Search's AI Mode (powered by Gemini) to search the web in real-time and return a comprehensive, grounded answer. Results include information from current web pages, news, and data.
This is equivalent to using Google Search's "AI Mode" tab — the AI reads multiple web sources and synthesizes an answer, similar to Perplexity or Grok's web search, but powered by Google's search index.
Args: query: Search query or question. Can be anything you'd type into Google. Examples: "latest news about AI regulation", "Bitcoin price today", "how does mRNA vaccine work", "Python asyncio best practices 2026"
Returns: A synthesized answer based on real-time web search results. The answer is grounded in actual web content found by Google.
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The tools 'ask' and 'web_search' have nearly identical descriptions, both using Google AI Mode and returning AI-generated answers. The only distinction is that 'ask' may optionally skip web search, but this is unclear and overlapping, making it hard for an agent to choose reliably.
Tool names 'ask' (verb) and 'web_search' (noun with underscore) do not follow a consistent pattern. Mixing a simple verb with a compound noun creates inconsistency, and no clear naming convention is evident across the set.
With only 2 tools, the server feels thin for a search service, but it is scoped to Google AI Mode. The count is borderline; it lacks additional tools for raw results or specialized searches, but the core functionality is covered.
For the narrow purpose of AI-powered search with synthesis, the server covers asking general questions and web searches. Minor gaps exist (e.g., no way to get unsynthesized results), but overall the surface is reasonably complete for its stated domain.
Maintenance
Related MCP Connectors
Free web search for AI agents. No API key required. Hosted MCP in active development.
Web search API and MCP server for developers building AI agents.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that enables AI models to perform Google Web searches using the Gemini API, complete with citations and grounding metadata for accurate information retrieval. It is compatible with Claude Desktop and other MCP clients for real-time web access.13Apache 2.0
- AlicenseAqualityDmaintenanceFree, unlimited web search MCP server using Gemini CLI's Google Search grounding to provide cited, live web results for any AI agent.31MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.MIT
- AlicenseNot gradedqualityDmaintenanceFree web search MCP server using SearXNG, supporting web search, news search, and search summaries.MIT