node2flow-google-drive
mcpsmitheryMCP server for Google Drive API v3 : search, read, create, share, and manage files and folders. ## Features - Search files with powerful query syntax (name, type, folder, date, full-text) - Read text file content and export Google Workspace files (Docs, Sheets, Slides) - Create, copy, rename, move, star, trash, and permanently delete files - Share files with users, groups, domains, or make public with role-based access - Add comments and threaded replies on files, resolve comment threads - Manage shared drives (create, list, delete) - View file revision history and storage quota ## 23 Tools - **Files (10):** search, get metadata, read content, create, update, copy, delete, export, create folder, empty trash - **Permissions (3):** list permissions, share file, unshare file - **Comments (3):** list, create, delete comments - **Replies (2):** list, create replies (with resolve/reopen actions) - **Shared Drives (3):** list, create, delete shared drives - **Revisions (1):** list file revision history - **About (1):** user info, storage quota, import/export formats ## Configuration - `GOOGLE_CLIENT_ID` : OAuth 2.0 Client ID from Google Cloud Console - `GOOGLE_CLIENT_SECRET` : OAuth 2.0 Client Secret - `GOOGLE_REFRESH_TOKEN` : Refresh token obtained via OAuth consent flow with `drive` scope (use Google OAuth Playground)
By Smithery | 57 findings | Scanned 5/15/2026 | tooltrust-scanner/v0.3.9
Risk Summary
Needs ApprovalExcessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (57)
tool declares network permission
gd_search_filesgd_read_filetool declares exec permission
gd_create_filegd_update_filegd_copy_filegd_create_folderFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool declares fs permission
gd_search_filesgd_get_filegd_read_filegd_create_filegd_update_filegd_copy_filegd_delete_filegd_export_filegd_create_foldergd_empty_trashgd_list_permissionsgd_share_filegd_unshare_filegd_list_commentsgd_create_commentgd_delete_commentgd_list_repliesgd_create_replygd_create_drivegd_delete_drivegd_list_revisionstool declares db permission
gd_list_drivesFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
gd_search_filesgd_read_filegd_create_filegd_update_filegd_copy_filegd_create_folderFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
gd_search_filesgd_get_filegd_read_filegd_create_filegd_update_filegd_copy_filegd_delete_filegd_export_filegd_create_foldergd_empty_trashgd_list_permissionsgd_share_filegd_unshare_filegd_list_commentsgd_create_commentgd_delete_commentgd_list_repliesgd_create_replygd_list_drivesgd_create_drivegd_delete_drivegd_list_revisionsgd_aboutFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y node2flow-google-drive"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)