answer_query_websearch
Answers a natural language query using the configured Vertex AI model (gemini-2.5-pro) enhanced with Google Search results for up-to-date information. Requires a 'query' string.
LABSCO SUMMARY
One model, seven shapes — because the prompt is the product here.
Every tool calls the same grounded model; what differs is the instruction wrapped around your input, which is why the snippet tool returns code without commentary and the comparison tool returns a table. That is genuinely useful and also the limit: the author says plainly that comparisons, architecture guidance and security findings are model output to check against the cited primary sources, not deterministic results. Two practical notes before wiring it up — a tool appearing in the list does not prove its provider is configured and reachable, and the default safety setting is BLOCK_NONE.
What it is
A research layer over a Gemini model with Google Search grounding, exposing task-shaped calls rather than one generic query box. It runs against either Vertex AI or the Gemini API, chosen at startup.
What you get
- A natural-language query answered against current search results rather than training data (answer_query_websearch).
- Documentation answered as prose or as code: a comprehensive explanation synthesised primarily from official documentation, or the exact snippet with the explanation stripped out (explain_topic_with_docs, get_doc_snippets).
- A code snippet compared against documented best practice, reporting potential bugs, performance issues and security vulnerabilities with citations and severity, scoped by language and analysis focus (code_analysis_with_docs).
- Technologies compared across criteria you name, returned as tables with pros, cons and use cases, including version-specific and compatibility notes (technical_comparison).
- Architecture patterns proposed for a described use case, with implementation examples and the tradeoffs behind each one (architecture_pattern_recommendation).
- A structured guidelines document generated from a list of technologies and versions, synthesised from current official documentation and style guides into actionable rules (generate_project_guidelines).
Requirements
Node.js 18 or newer and Bun. Then one of two providers, set with AI_PROVIDER: vertex needs a Google Cloud project with billing and the Vertex AI API enabled, GOOGLE_CLOUD_PROJECT set, and Application Default Credentials configured; gemini needs only GEMINI_API_KEY. GOOGLE_CLOUD_LOCATION defaults to us-central1, and the model, temperature, streaming, max output tokens and retry behaviour are all environment variables. A Docker image is the other route — with credentials mounted read-only rather than baked in. Note that safety filters are set to BLOCK_NONE by default.
Setup effort
One command plus credentials — bunx google-ai-search-mcp, then supply credentials
USE CASES
01
Answering a question about a library released after the model's cutoff
The answer is grounded in search results rather than in what the model remembers.
02
Getting the exact call signature without a paragraph around it
One tool returns prose, the other returns the snippet — pick by what you are about to do with it.
03
Reviewing code against the documentation rather than against habit
The findings come back with citations and severity, scoped to the language and the concern you named.
04
Choosing between two frameworks
Compare them on your own criteria, then verify the numbers against the sources it cites.
05
Deciding how to structure a new system
Get patterns with their tradeoffs rather than one recommendation with no alternatives.
06
Writing the conventions doc for a new project
Generate the rules from the current documentation for each item in the stack, with versions.
7 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
architecture_pattern_recommendation
Suggests architecture patterns for specific use cases based on industry best practices. Provides implementation examples and considerations for the recommended patterns. Includes diagrams and explanations of pattern benefits and tradeoffs. Uses the configured Vertex AI model (gemini-2.5-pro) with Google Search. Requires 'requirements' and 'tech_stack'.
code_analysis_with_docs
Analyzes code snippets by comparing them with best practices from official documentation found via web search. Identifies potential bugs, performance issues, and security vulnerabilities. Uses the configured Vertex AI model (gemini-2.5-pro) with Google Search. Requires 'code', 'language', and 'analysis_focus'.
explain_topic_with_docs
Provides a detailed explanation for a query about a specific software topic by synthesizing information primarily from official documentation found via web search. Focuses on comprehensive answers, context, and adherence to documented details. Uses the configured Vertex AI model (gemini-2.5-pro) with Google Search. Requires 'topic' and 'query'.
generate_project_guidelines
Generates a structured project guidelines document (e.g., Markdown) based on a specified list of technologies and versions (tech stack). Uses web search to find the latest official documentation, style guides, and best practices for each component and synthesizes them into actionable rules and recommendations. Uses the configured Vertex AI model (gemini-2.5-pro) with Google Search. Requires 'tech_stack'.
get_doc_snippets
Provides precise, authoritative code snippets or concise answers for technical queries by searching official documentation. Focuses on delivering exact solutions without unnecessary explanation. Uses the configured Vertex AI model (gemini-2.5-pro) with Google Search. Requires 'topic' and 'query'.
technical_comparison
Compares multiple technologies, frameworks, or libraries based on specific criteria. Provides detailed comparison tables with pros/cons and use cases. Includes version-specific information and compatibility considerations. Uses the configured Vertex AI model (gemini-2.5-pro) with Google Search. Requires 'technologies' and 'criteria'.
BEFORE YOU INSTALL
What to know first
Tools you get
7 tools when we connected. Tools are listed whether or not Vertex or Gemini is configured, so a listed tool may not work.
Requires
- Node.js 18+
- Bun on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 7 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
bunx google-ai-search-mcpMCP Clients
Cline — bunx
CLINE — BUNX · JSON
{
"mcpServers": {
"google-ai-search-mcp": {
"command": "bunx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"AI_PROVIDER": "vertex",
"GOOGLE_CLOUD_PROJECT": "<YOUR_GOOGLE_CLOUD_PROJECT>",
"VERTEX_MODEL_ID": "gemini-2.5-pro",
"GEMINI_MODEL_ID": "gemini-2.5-pro",
"GOOGLE_CLOUD_LOCATION": "us-central1",
"AI_TEMPERATURE": "0.0",
"AI_USE_STREAMING": "true",
"AI_MAX_OUTPUT_TOKENS": "65536",
"AI_MAX_RETRIES": "3",
"AI_RETRY_DELAY_MS": "1000"
},
"disabled": false,
"alwaysAllow": [],
"timeout": 3600
}
}
}Cline — local build
CLINE — LOCAL BUILD · TERMINAL
git clone https://github.com/shariqriazz/google-ai-search-mcp.git
cd google-ai-search-mcp
bun install
bun run buildCLINE — LOCAL BUILD · JSON
{
"mcpServers": {
"google-ai-search-mcp": {
"command": "node",
"args": [
"<YOUR_PATH_TO_GOOGLE_AI_SEARCH_MCP>/build/index.js"
],
"env": {
"AI_PROVIDER": "vertex",
"GOOGLE_CLOUD_PROJECT": "<YOUR_GOOGLE_CLOUD_PROJECT>",
"VERTEX_MODEL_ID": "gemini-2.5-pro",
"GEMINI_MODEL_ID": "gemini-2.5-pro",
"GOOGLE_CLOUD_LOCATION": "us-central1",
"AI_TEMPERATURE": "0.0",
"AI_USE_STREAMING": "true",
"AI_MAX_OUTPUT_TOKENS": "65536",
"AI_MAX_RETRIES": "3",
"AI_RETRY_DELAY_MS": "1000"
},
"disabled": false,
"alwaysAllow": [],
"timeout": 3600
}
}
}<YOUR_PATH_TO_GOOGLE_AI_SEARCH_MCP> is the absolute path of your clone. Bun run build writes build/index.js there.
