SAFE DOCX TOOLS

23 tools from the Safe Docx MCP Server, categorised by risk level.

View the Safe Docx policy →

READ TOOLS

7

WRITE TOOLS

13
accept_changes Accept all tracked changes in the document body, producing a clean document with no revision markup. Returns acceptance stats. 2/5 add_comment Add a comment or threaded reply to a document. Provide target_paragraph_id + anchor_text for root comments, or parent_comment_id for replies. 3/5 add_footnote Add a footnote anchored to a paragraph. Optionally position the reference after specific text using after_text. Note: [^N] markers in read_file out... 3/5 apply_plan Validate and apply a batch of edit steps (replace_text, insert_paragraph) to a document in one call. Validates all steps first; applies only if all... 3/5 close_file Close an open file session, or close all sessions with explicit confirmation. Supports DOCX and Google Docs. 3/5 compare_documents Compare two DOCX documents and produce a tracked-changes output document. Provide original_file_path + revised_file_path for standalone comparison,... 2/5 format_layout Apply layout controls (paragraph spacing, table row height, cell padding). Google Docs supports paragraph spacing only. 2/5 init_plan Initialize revision-bound context metadata for coordinated multi-agent planning. 3/5 insert_paragraph Insert a paragraph before/after an anchor paragraph by _bk_* id. Supports DOCX and Google Docs. 3/5 merge_plans Deterministically merge multiple sub-agent plans and detect hard conflicts before apply. 2/5 replace_text Replace text in a paragraph by _bk_* id, preserving formatting. Supports DOCX and Google Docs. 3/5 save Save document. For DOCX: saves clean and/or tracked changes output. For Google Docs: checkpoint (default) returns revisionId, or snapshot exports a... 3/5 update_footnote Update the text content of an existing footnote. 3/5

DESTRUCTIVE TOOLS

3
How many tools does the Safe Docx MCP server have? +

The Safe Docx MCP server exposes 23 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Safe Docx tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Safe Docx server.

What risk categories do Safe Docx tools fall into? +

Safe Docx tools are categorised as Read (7), Write (13), Destructive (3). Each category has a recommended default policy.

Enforce policies on Safe Docx

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.