node2flow-google-docs
mcpsmitheryMCP server for Google Docs : create, read, edit, format, and manage documents through 26 tools. ## Features - Create and read document content with full structure - Insert, delete, and replace text at any position - Format text: bold, italic, underline, fonts, colors, links - Paragraph styles: alignment, spacing, headings (H1-H6) - Bulleted and numbered lists - Tables: insert, add/delete rows and columns, merge cells - Headers, footers, and section breaks - Named ranges for bookmarking content - Raw batchUpdate for any Docs API operation ## 26 Tools - **Document**: create and get document content - **Content**: insert text, delete, replace all, insert image, page break - **Text Formatting**: update text style, update paragraph style - **Lists**: create and delete bullets/numbering - **Tables**: insert table, add/delete rows and columns, merge/unmerge cells - **Headers & Footers**: create and delete headers and footers - **Sections & Named Ranges**: section breaks, create and delete named ranges - **Advanced**: raw batchUpdate pass-through ## 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 with documents scope
By Smithery | 47 findings | Scanned 4/28/2026 | tooltrust-scanner/v0.3.9
Risk Summary
Needs ApprovalDep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
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 (47)
tool declares network permission
gdoc_insert_inline_imagegdoc_update_text_styleFix: 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
gdoc_creategdoc_delete_contentgdoc_update_text_stylegdoc_update_paragraph_stylegdoc_create_bulletsgdoc_delete_bulletsgdoc_delete_table_rowgdoc_delete_table_columngdoc_create_headergdoc_create_footergdoc_delete_headergdoc_delete_footergdoc_create_named_rangegdoc_delete_named_rangegdoc_batch_updateFix: 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
gdoc_insert_inline_imagegdoc_update_text_styleFix: 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.
input schema exposes 19 properties (threshold: 10)
gdoc_update_text_styleinput schema exposes 13 properties (threshold: 10)
gdoc_update_paragraph_styleFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
gdoc_creategdoc_getgdoc_insert_textgdoc_delete_contentgdoc_replace_all_textgdoc_insert_inline_imagegdoc_insert_page_breakgdoc_update_text_stylegdoc_update_paragraph_stylegdoc_create_bulletsgdoc_delete_bulletsgdoc_insert_tablegdoc_insert_table_rowgdoc_insert_table_columngdoc_delete_table_rowgdoc_delete_table_columngdoc_merge_table_cellsgdoc_unmerge_table_cellsgdoc_create_headergdoc_create_footergdoc_delete_headergdoc_delete_footergdoc_insert_section_breakgdoc_create_named_rangegdoc_delete_named_rangegdoc_batch_updateFix: 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-docs"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)