gemini-mcp-tool MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Tap Gemini's ~1M-token context from within Claude
@ syntax references files and directories
sandbox-test runs code safely in Gemini's sandbox
Slash commands in Claude Code (/analyze, /sandbox, /help, /ping)
Simple claude mcp add install

라이브 데모

실제 사용 모습

gemini-mcp-tool.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "gemini-mcp-tool": {
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-tool"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "gemini-mcp-tool": {
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-tool"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "gemini-mcp-tool": {
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-tool"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "gemini-mcp-tool": {
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-tool"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "gemini-mcp-tool",
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-tool"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "gemini-mcp-tool": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "gemini-mcp-tool"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add gemini-mcp-tool -- npx -y gemini-mcp-tool

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: gemini-mcp-tool

How to analyze a massive file that doesn't fit Claude's context

👤 Developers working with giant logs, codebases, or documents ⏱ ~15 min intermediate

언제 쓸까: Claude can't fit the file, but Gemini can.

사전 조건

Gemini CLI + Google API key — npm i -g @google/gemini-cli; then gemini config set with your key from aistudio.google.com
Install MCP — claude mcp add gemini-cli -- npx -y gemini-mcp-tool

흐름

Offload analysis

ask-gemini: @/var/log/app-2026-04.log — find all 5xx errors clustered around deploys in the last 72h, produce a table.✓ 복사됨

→ Gemini analyzes, returns compact summary
Drill in with Claude

Based on Gemini's summary, focus on the cluster around 2026-04-12 14:30 UTC and propose a root cause.✓ 복사됨

→ Claude reasons over the summary

결과: Result that neither model alone could produce in one shot.

함정

Sending sensitive logs to Gemini — Strip PII before invoking ask-gemini or use a self-hosted model instead
Token cost on Gemini Pro for huge inputs — Use Gemini Flash for cost; Pro only when accuracy matters

함께 쓰기: filesystem

How to review an entire small codebase in one shot

👤 Engineers auditing small services ⏱ ~20 min intermediate

언제 쓸까: You want a holistic review that considers every file at once.

흐름

Hand the whole repo

ask-gemini: @./src/ — review for structural issues, repeated patterns that should be abstracted, and dead code.✓ 복사됨

→ Repo-wide observations
Triage suggestions

Of those, which 3 are highest impact? Name the files.✓ 복사됨

→ Prioritized list

결과: A reviewer's first pass produced in one prompt.

함정

Gemini loses detail on huge repos — If your src/ exceeds 500k tokens, narrow to subdirectories

함께 쓰기: github

How to execute unsafe code in Gemini's sandbox

👤 Devs testing untrusted code snippets ⏱ ~5 min beginner

언제 쓸까: You want to try running something without letting it touch your machine.

흐름

Submit to sandbox

sandbox-test: run this Python script [paste] — report stdout/stderr and exit code.✓ 복사됨

→ Output without side effects on your machine

결과: Safe execution result.

함정

Sandbox doesn't have internet by default for most snippets — Check Gemini CLI sandbox docs for connectivity options

조합

다른 MCP와 조합해 10배 효율

gemini-mcp-tool + filesystem

Pick files locally, pass @-references to Gemini

List all *.log files modified today via filesystem, then ask-gemini @ each to find anomalies.✓ 복사됨

gemini-mcp-tool + github

Review a PR by handing the full diff to Gemini's wide context

Fetch PR #4421 diff via github MCP, then ask-gemini to critique the whole diff as one coherent change.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
ask-gemini	prompt: str (may include @path refs), model?: 'flash'\|'pro'	Large-context analysis	Gemini API call — Flash ~$0.075/1M input, Pro higher
sandbox-test	code: str, language?	Run untrusted code	Gemini sandbox billing
Ping		Sanity-check connection	free

비용 및 제한

운영 비용

API 쿼터: Gemini AI Studio has free tier; paid tier is pay-per-token
호출당 토큰: Large — this is the whole point. Plan for 100k-500k tokens per call.
금액: Gemini 2.5 Flash ~$0.075 per 1M input; Pro is ~20x more
팁: Default to Flash. Escalate to Pro only when Flash is clearly wrong.

보안

권한, 시크릿, 파급범위

최소 스코프: Gemini API key

자격 증명 저장: Gemini CLI stores key in ~/.config/gemini/

데이터 외부 송신: File content goes to Google Gemini; subject to Google's Gemini API data policy

절대 부여 금지: Don't pass secrets in @-referenced files — they go straight to Google

Files sent via @ are uploaded to Gemini — treat as you would any cloud upload.

문제 해결

자주 발생하는 오류와 해결

gemini-cli not found

Install globally: npm i -g @google/gemini-cli; ensure npm global bin is on PATH.

확인: which gemini

401 from Gemini

Run gemini config to set your API key from aistudio.google.com.

확인: gemini 'hello'

Token limit exceeded

Even Gemini has caps; trim @-references or use search to narrow files first.

Sandbox timeout

Long-running code needs higher timeout; or run locally in a container instead.

대안

gemini-mcp-tool 다른 것과 비교

대안	언제 쓰나	단점/장점
deep-research MCP	You want autonomous research, not raw Gemini access	Different shape; includes web search
openrouter MCP	You want multi-model access via one key	No @-file syntax; less convenient for big-context

gemini-mcp-tool