Atlas / MCP servers / infolabai / Gemini

GeminiSAFE

mcp/infolabai/gemini-13
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 0r · 1w · 0d
Transport
—
License
MIT
Stars
30
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

English Version

Claude Code에서 Gemini AI를 MCP 서버로 사용할 수 있게 해주는 도구입니다.

주요 이점

  1. 대용량 파일 분석: Gemini의 거대한 컨텍스트 윈도우를 활용하여 대용량 파일과 디렉토리를 한 번에 분석 가능
  2. 토큰 절약: 무료로 제공되는 Gemini CLI를 이용해서 Claude Code의 토큰 사용량을 절약하면서도 Claude Code만의 강력한 기능을 활용 가능
  3. 간편한 통합: 기존 Claude Code 워크플로우에 쉽게 통합 가능

이 서버는 로컬에 설치된 gemini CLI 도구를 사용하여 작동합니다.

사전 요구사항

빠른 시작

1. 저장소 클론

git clone https://github.com/InfolabAI/gemini-cli-mcp.git
cd gemini-cli-mcp
  • uv 설치

uv는 시스템 레벨에 설치해야 합니다 (Python 가상환경과 독립적으로 작동):

# Linux/macOS (권장)
curl -LsSf https://astral.sh/uv/install.sh | sh

# macOS Homebrew
brew install uv

# Windows PowerShell
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

# 설치 확인
uv --version
  • 의존성 설치:
uv sync

Tools

  • run_gemini
  • Gemini를 이용해서 파일, 디렉토리, URL의 대량 정보를 처리합니다
  • 입력:
  • prompt (string): Gemini에 전달할 프롬프트
  • file_dir_url_path (string): 분석할 파일, 디렉토리 또는 URL 경로
  • working_directory (string): 작업 디렉토리 (필수)

Configuration

Claude Code에서 사용하려면 MCP 서버 설정을 추가하세요:

Linux 의 경우, ~/.claude.json 파일에 다음 설정을 추가:

{
"mcpServers": {
"gemini": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/project",
"run",
"python",
"/path/to/your/project/gemini_mcp_server.py"
],
"env": {}
}
}
}

참고: /path/to/your/project/를 다운받은 git 프로젝트 경로로 변경하세요.

개발

  • 서버 직접 실행(실행 후, 멈춰있는 것이 정상임)
uv run python gemini_mcp_server.py
  • 테스트
uv run python test_gemini_mcp.py
  • Debugging

MCP 서버는 stdio를 통해 통신하므로 디버깅이 어려울 수 있습니다. MCP Inspector 사용을 권장합니다.

  • 주의할 점

subprocess.run 을 사용할 때 shell=True 옵션을 사용해야 합니다. 이는 MCP 서버 환경에서 쉘을 통해 명령을 실행하기 위함입니다. 이 옵션이 없으면, Gemini CLI 명령 실행 시, 대기 상태에

Read from source at commit 1be34b58f97dOBSERVED · 2026-10-08
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add gemini-mcp-server -- uvx gemini-mcp-server
claude-desktop
{
  "mcpServers": {
    "gemini-mcp-server": {
      "command": "uvx",
      "args": [
        "gemini-mcp-server"
      ]
    }
  }
}
03

Exposed tools (1)

0 read · 1 write · 0 destructive.

ToolRiskDescription
run_geminiwrite
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
declared (1 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (3)

LOWSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:35
curl -LsSf https://astral.sh/uv/install.sh | sh
LOWSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README_EN.md:35
curl -LsSf https://astral.sh/uv/install.sh | sh
LOWSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README_EN.md:52
curl -fsSL https://gemini.replit.com/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 1be34b58f97dfull audit observations/trust-audit/mcp-server/infolabai__gemini-13.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-081be34b58f97dSAFEB89first audit
06

Questions

What tools does Gemini expose?

1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Gemini safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Gemini need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (1be34b58f97d), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement