Borrowing it
Nothing to install: this file belongs to pghoya2956/Google-Drive-MCP-Server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pghoya2956/Google-Drive-MCP-Server/main/CLAUDE.mdgit clone --depth 1 https://github.com/pghoya2956/Google-Drive-MCP-ServerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/pghoya2956/google-drive-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/pghoya2956/google-drive-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/pghoya2956/google-drive-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/pghoya2956/google-drive-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/pghoya2956/google-drive-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02247 | $0.02247 |
| Opus 5 | $0.01123 | $0.01123 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
Google-Drive-MCP-Server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Drive MCP Server 프로젝트 정보
프로젝트 개요
- 패키지명: @pghoya2956/google-drive-mcp-server
- GitHub 저장소: https://github.com/pghoya2956/Google-Drive-MCP-Server
- npm: https://www.npmjs.com/package/@pghoya2956/google-drive-mcp-server
- 설명: Model Context Protocol (MCP)을 통해 Google Drive와 Google Sheets에 접근하는 서버
- 작성자: pghoya2956
주요 아키텍처
graph TD
A[MCP Client<br/>예: Claude Desktop] -->|MCP Protocol| B[gdrive-mcp-server]
B -->|OAuth2| C[Google API]
C --> D[Google Drive]
C --> E[Google Sheets]
F[환경변수] -->|설정| B
G[인증 파일들] -->|토큰| B
subgraph "인증 파일"
G1[gcp-oauth.keys.json<br/>최초 인증용]
G2[.gdrive-server-credentials.json<br/>토큰 저장]
end
G1 --> G
G2 --> G
인증 메커니즘
- 최초 인증:
gcp-oauth.keys.json파일로 브라우저 인증 시작 - 토큰 저장:
.gdrive-server-credentials.json에 access/refresh 토큰 저장 - 토큰 갱신: 환경변수
CLIENT_ID/CLIENT_SECRET으로 자동 갱신 - 백그라운드 갱신: 45분마다 토큰 유효성 확인 및 갱신
접근 범위 제어
GDRIVE_ROOT_FOLDER_ID로 지정된 폴더와 하위 폴더만 접근- 내 드라이브와 공유 드라이브 모두 지원
supportsAllDrives: trueAPI 옵션으로 모든 드라이브 유형 지원
설치 방법
# npm으로 설치
npm install git+https://github.com/pghoya2956/Google-Drive-MCP-Server.git
# 또는 npm 레지스트리에서 (퍼블리싱 후)
npm install @pghoya2956/google-drive-mcp-server
주요 도구
gdrive_search: 파일 검색gdrive_read_file: 파일 읽기 (PDF 메타데이터 추출 및 Excel 파일 지원)gdrive_read_large_file: 대용량 파일 읽기gdrive_folder_structure: 폴더 구조 탐색gdrive_analyze_image: 이미지 분석gsheets_read: Google Sheets 읽기 (Excel 파일은 미지원)gsheets_update_cell: 셀 업데이트
PDF 파일 지원 (v0.3.0)
기능
- 텍스트 추출: pdf-parse 라이브러리를 사용한 텍스트 추출
- 메타데이터: 페이지 수, 파일 크기, 제목, 작성자, 생성일 등
- 구조화된 응답: JSON 형식으로 텍스트와 메타데이터 분리 제공
제한사항
- 파일 크기 제한: 기본 20MB (환경 변수
PDF_SIZE_LIMIT_MB로 최대 100MB까지 조정 가능) - 암호화된 PDF 미지원
- 스캔된 이미지 PDF 텍스트 추출 불가
- OCR 기능 없음
개선된 에러 처리
- 파일 크기 초과 시 명확한 안내 메시지
- 암호화/스캔 PDF에 대한 사용자 친화적 오류 메시지
- 각 오류 유형에 대한 해결 방법 제안
PDF 캐싱 기능 (v0.3.0)
LRU 캐시 구현
- 메모리 제한: 100MB 최대 크기
- TTL: 30분 자동 만료
- 캐시 키: fileId + modifiedTime 조합
- 정리: 10분마다 만료된 항목 자동 제거
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 217 lines · 2,247 tokens per session scan A c90ed83174e5
Google-Drive-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository pghoya2956/Google-Drive-MCP-Server (1 stars, last pushed 1y ago), licensed MIT. It adds 2,247 tokens to every session, about $0.0112 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.