
Gcs
com.pulsemcp由 pulsemcp.com 發布v0.1.14更新於 Oct 24, 2026
MCP server for Google Cloud Storage with fine-grained tool access control.
概覽
針對 Google Cloud Storage 的本機 MCP 伺服器,讓助理列出、讀取、上傳、複製和刪除值區與物件,並可用工具群組限制權限。
- 可以做什麼
- 列出並檢視值區和物件,檢查值區是否存在及可存取,讀取物件文字內容,或將物件及整個前綴以原始位元組下載到本機磁碟。以內嵌文字、單一本機檔案或整個目錄樹上傳或更新物件,並在同一或不同值區間複製物件。建立值區,刪除物件或空值區,實際可用範圍取決於啟用的工具群組。透過工具群組(readonly、readwrite、delete)或個別啟用/停用清單控制可用工具,並可將所有操作限制在單一值區內。
- 適用情境
- 適合助理需要處理 Google Cloud Storage 中檔案的情境:瀏覽和讀取已存資料、把本機檔案或資料夾移入值區、複製物件,或清理物件和值區。唯讀群組適合探索與分析,單一值區模式適合最小權限設定。
- 執行需求
- 透過 npx 在本機執行(需要 Node.js)。需要 GCS_PROJECT_ID 和 Google Cloud 憑證:以 GCS_SERVICE_ACCOUNT_KEY_FILE 提供服務帳戶金鑰檔案、以 GCS_SERVICE_ACCOUNT_KEY_JSON 提供內嵌金鑰 JSON,或使用 gcloud 的 Application Default Credentials。服務帳戶需具備所啟用工具對應的儲存 IAM 權限。需要連線至 Google Cloud Storage 的網路。
安裝
README
GCS MCP Server
MCP server for Google Cloud Storage operations with fine-grained tool access control. Supports read/write operations on GCS buckets and objects, with configurable tool groups for security and permission management.
Highlights
- Full GCS bucket and object management (list, get, put, copy, delete)
- Fine-grained access control with tool groups (readonly, readwrite, delete)
- Individual tool enable/disable via environment variables
- Multiple authentication methods (service account key file, inline JSON, ADC)
- GCS credential validation with health checks
- Single bucket constraint mode
- TypeScript with strict type checking
- Comprehensive testing (functional, integration, manual)
Capabilities
Tools
Downloading to Local Disk
get_object returns an object's contents inline as UTF-8 text, which is lossy for binary data and impractical for large files or many files at once. For local data-wrangling, use the download tools instead — both stream raw bytes to disk and belong to the readonly toolgroup:
-
download_object— download a single object to a local file path. Defaults to a unique file under the OS temp directory. -
download_prefix— recursively download every object under a prefix to a local directory, preserving the key path structure as subdirectories. Paginates through the full listing, skips directory-placeholder objects (keys ending in/), collects per-object errors without aborting the batch, and returns a manifest:The inline
fileslist is capped (maxInlineEntries, default 100), butobjectCountandtotalBytesalways reflect the full download. WhendestinationDiris omitted it defaults to a unique folder under the OS temp directory.
Uploading from Local Disk
put_object takes the object content inline as a string argument, which routes every byte through the model context and requires base64 for binary data — impractical for large files or bulk uploads. For uploading files or folders without consuming context, use the local-path upload tools instead. Both stream raw bytes directly from disk to GCS server-side, returning only metadata. They belong to the readwrite toolgroup, so read-only deployments never gain them.
-
put_object_from_path— upload a single local file by streaming it from a filesystem path. Content type is auto-detected from the file extension (override withcontentType). Binary files (images, archives) work without base64. Returns{ bucket, key, sourcePath, size, etag, generation }. -
upload_prefix— recursively upload every file under a local directory, preserving the directory structure as key paths beneath a destination prefix. Symbolic links to files are followed and uploaded (links to directories are skipped to avoid cycles), per-file failures are collected without aborting the batch, and it returns a manifest:The inline
fileslist is capped (maxInlineEntries, default 100), butobjectCountandtotalBytesalways reflect the full upload. WhendestPrefixis omitted, files upload to the bucket root.
Resources
Tool Groups
Control which tools are available via the GCS_ENABLED_TOOLGROUPS environment variable:
Examples:
GCS_ENABLED_TOOLGROUPS="readonly"- Only read operationsGCS_ENABLED_TOOLGROUPS="readonly,readwrite"- Read and write, no deletesGCS_ENABLED_TOOLGROUPS="readonly,readwrite,delete"- All operations- Not set - All tools enabled (default)
Individual Tool Control
Fine-grained control over specific tools:
GCS_ENABLED_TOOLS="list_buckets,get_object"- Only enable these toolsGCS_DISABLED_TOOLS="delete_bucket,delete_object"- Disable these tools
Single Bucket Mode
Constrain all operations to a specific bucket using GCS_BUCKET:
When set:
- All object operations are automatically scoped to this bucket
- Bucket-level tools (
list_buckets,create_bucket,delete_bucket,head_bucket) are hidden - The
bucketparameter is automatically injected and hidden from tool inputs - For
copy_object, both source and destination are constrained to the specified bucket
This lets you grant a least-privilege service account that has only object-level access to one bucket, without project-level bucket-listing permission. The startup healthcheck honors this: when GCS_BUCKET is set it validates credentials with an object-scoped probe (storage.objects.list on that bucket) and never calls the project-level bucket list or a bucket-metadata probe. See Required IAM permissions for the exact permissions per mode.
Required IAM permissions
The minimal IAM permissions depend on whether the server is constrained to a single bucket (GCS_BUCKET) and which tool groups you enable. The startup healthcheck validates credentials within these bounds — it does not require any permission beyond what the table below lists for your mode.
Startup healthcheck
Set SKIP_HEALTH_CHECKS=true to bypass startup validation entirely (disables all credential checks — not recommended).
Per-tool permissions
Beyond the healthcheck, each tool needs the corresponding GCS permission at runtime. Grant only what the tool groups you enable require:
For a read-only, single-bucket service account, the roles/storage.objectViewer role on the bucket (or a custom role with storage.objects.list + storage.objects.get) is sufficient — no project-level or bucket-metadata permissions are needed.
Quick Start
Configuration
Environment Variables
Authentication
The server supports three authentication methods (in order of precedence):
- Service Account Key File: Set
GCS_SERVICE_ACCOUNT_KEY_FILEto the path of a JSON key file - Inline Service Account Key: Set
GCS_SERVICE_ACCOUNT_KEY_JSONwith the JSON contents directly - Application Default Credentials (ADC): No additional env vars needed - uses
gcloud auth application-default login
Claude Desktop Configuration
If this is your first time using MCP Servers, make sure you have the Claude Desktop application and follow the official MCP setup instructions.
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop and you should be ready to go!
Read-Only Mode
For safer exploration, enable only read operations:
Using Application Default Credentials
If you have gcloud CLI configured locally:
Then configure without key file:
Development
Install Dependencies
Build
Running in Development Mode
Testing
Manual Testing Setup
Create a .env file in the gcs directory:
Then run:
Project Structure
License
MIT
來源:experimental/gcs/README.md,提交 0ed34de
工具
0版本歷史
1- v0.1.14最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分