Google AI Search MCP

This project implements a Model Context Protocol (MCP) server that provides a comprehensive suite of Google AI-powered search and documentation tools specifically designed to help AI coders overcome LLM knowledge gaps and information limitations. Its 7 documented tools cover with, docs. It runs locally over stdio via the published package.

People connecting documentation tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-11 · ★ 6 · #91 OF 183 MAINTAINED DOCUMENTATION · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Google AI Search MCP

before you install - you'll need

Set GEMINI_API_KEY before connecting. AI_PROVIDER is optional or environment-specific per the README.

Claude Code

claude mcp add shariqriazz-google-ai-search-mcp -- npx -y google-ai-search-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "shariqriazz-google-ai-search-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "google-ai-search-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package google-ai-search-mcp - unscoped; check the name against the project README before installing

registry namespace io.github.shariqriazz is GitHub-verified and matches the repo owner

03 · What Google AI Search MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

An agent gets 7 documented tools spanning with, docs, including answer_query_websearch, explain_topic_with_docs, get_doc_snippets, generate_project_guidelines.

Capability map

Tools grouped from the project's README - what Google AI Search MCP lets an agent do.

Answer

1 tool - e.g. Developer-focused natural language queries with automatic technical detection, enhanced search methodology, and comprehensive code formatting using Google AI wi

answer_query_websearch

Explain

1 tool - e.g. Streamlined technical explanations with improved debugging scenarios, synthesizing information from official documentation with reduced verbosity and enhanced t

explain_topic_with_docs

read & search

1 tool - e.g. Enhanced code snippet retrieval with progressive complexity examples, advanced search patterns, version-specific targeting, and comprehensive context for techni

get_doc_snippets

Generate

1 tool - e.g. Generates comprehensive structured project guidelines documents based on specified technologies, using web search for current best practices and industry standa

generate_project_guidelines

Code

1 tool - e.g. Evidence-based code analysis with standardized citations, severity categorization, and actionable recommendations by comparing code against official documentati

code_analysis_with_docs

Technical

1 tool - e.g. Produces technology comparisons across requested criteria using current search context where available. Verify quantitative or market claims against the cited p

technical_comparison

Architecture

1 tool - e.g. Produces architecture options, tradeoffs, and implementation considerations for a described use case. Validate the recommendation against the system's actual co

architecture_pattern_recommendation

04 · Who maintains Google AI Search MCP

Google AI Search MCP is maintained by shariqriazz. It's the only MCP server we track from this author; the repo dates to Jun 2025.

05 · Facts

repository: github.com/shariqriazz/google-ai-search-mcp
category: documentation - ranked #91 of 183 actively-maintained documentation servers as of 2026-08-25.
registry: io.github.shariqriazz/google-ai-search-mcp (active, first published 2026-08-11)
packages: npm:google-ai-search-mcp

06 · Google AI Search MCP FAQ

Is Google AI Search MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-11. We re-verify nightly.

What can Google AI Search MCP do?

An agent gets 7 documented tools spanning with, docs, including answer_query_websearch, explain_topic_with_docs, get_doc_snippets, generate_project_guidelines.

How do I install Google AI Search MCP?

Run `npx -y google-ai-search-mcp`. The README documents 2 environment variables (AI_PROVIDER, GEMINI_API_KEY) to set first. Set GEMINI_API_KEY before connecting. AI_PROVIDER is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Google AI Search MCP run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Google AI Search MCP

Alternatives to Google AI Search MCP

Maintained documentation servers if Google AI Search MCP isn't the fit.

Pairs well with

Servers that cover what Google AI Search MCP doesn't - only shown when the pairing reason fits the companion.

More documentation MCP servers · SignNow Api Helper MCP · Soracom Knowledge · Sprintra · Svelte MCP · Pulse8 AI Cortex Knowledge Vault

More TypeScript MCP servers · AI Visibility · Whoop · Constellation · Image · Local RAG (shinpr) · see all