Gemini DeepSearch MCP는 Google Gemini 모델과 Google 검색을 활용하여 깊이, 다중 단계 웹 연구를 수행하는 자동화 된 연구 에이전트입니다. 그것은 정교한 쿼리를 생성, 검색 결과에서 정보를 종합, 지식 격차를 식별, 높은 품질의 생산, 인용 풍부한 답변.

특징

• ** Gemini 모델 및 Google 검색을 사용하여 자동화 된 다중 단계 연구 **
• FastMCP 통합 HTTP API와 stdio 배포
• **물량 설정 ** (낮, 중간, 높은) 연구 깊이
• **Citation-rich 응답 ** 소스 추적
• **LangGraph-powered 워크플로우 ** 상태 관리

사용법

개발 서버 (HTTP + 스튜디오 UI)

Studio UI를 가진 LangGraph 개발 서버를 시작하십시오:

# 로컬 MCP 서버 (스트디오)

MCP 클라이언트와 통합을 위한 stdio 수송을 가진 MCP 서버 시작:

테스트

테스트 스위트를 실행:

MCP stdio 서버를 시험하십시오:

MCP 검사기 사용

Langsmith 추적

API를

deep_search 도구는 다음과 같습니다. -query (문자): 연구 질문 또는 주제는 조사

• ** effort** (string): 연구 노력 수준 - “low”, “medium”, 또는 “high”
• ** 낮은 ** : 1 쿼리, 1 루프, 플래시 모델

Gemini DeepSearch MCP

Gemini DeepSearch MCP is an automated research agent that leverages Google Gemini models and Google Search to perform deep, multi-step web research. It generates sophisticated queries, synthesizes information from search results, identifies knowledge gaps, and produces high-quality, citation-rich answers.

Features

• Automated multi-step research using Gemini models and Google Search
• FastMCP integration for both HTTP API and stdio deployment
• Configurable effort levels (low, medium, high) for research depth
• Citation-rich responses with source tracking
• LangGraph-powered workflow with state management

Usage

Development Server (HTTP + Studio UI)

Start the LangGraph development server with Studio UI:

make dev

Local MCP Server (stdio)

Start the MCP server with stdio transport for integration with MCP clients:

make local

Testing

Run the test suite:

make test

Test the MCP stdio server:

make test_mcp

Use MCP inspector

make inspect

With Langsmith tracing

GEMINI_API_KEY=AI******* LANGSMITH_API_KEY=ls******* LANGSMITH_TRACING=true make inspect

API

The deep_search tool accepts:

• query (string): The research question or topic to investigate
• effort (string): Research effort level - “low”, “medium”, or “high”
  • Low: 1 query, 1 loop, Flash model
  • Medium: 3 queries, 2 loops, Flash model
  • High: 5 queries, 3 loops, Pro model

Return Format

HTTP MCP Server (Development mode):

• answer: Comprehensive research response with citations
• sources: List of source URLs used in research

Stdio MCP Server (Claude Desktop integration):

• file_path: Path to a JSON file containing the research results

The stdio MCP server writes results to a JSON file in the system temp directory to optimize token usage. The JSON file contains the same answer and sources data as the HTTP version, but is accessed via file path rather than returned directly.

Requirements

• Python 3.12+
• GEMINI_API_KEY environment variable

Installation

Install directly using uvx:

uvx install gemini-deepsearch-mcp

Claude Desktop Integration

To use the MCP server with Claude Desktop, add this configuration to your Claude Desktop config file:

macOS

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-deepsearch": {
      "command": "uvx",
      "args": ["gemini-deepsearch-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      },
      "timeout": 180000
    }
  }
}

Windows

Edit %APPDATA%/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-deepsearch": {
      "command": "uvx",
      "args": ["gemini-deepsearch-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      },
      "timeout": 180000
    }
  }
}

Linux