SAFE DOCX TOOLS

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

WRITE 13 tools
Write accept_changes Accept all tracked changes in the document body, producing a clean document with no revision markup. Return... Write add_comment Add a comment or threaded reply to a document. Provide target_paragraph_id + anchor_text for root comments,... Write add_footnote Add a footnote anchored to a paragraph. Optionally position the reference after specific text using after_t... Write apply_plan Validate and apply a batch of edit steps (replace_text, insert_paragraph) to a document in one call. Valida... Write close_file Close an open file session, or close all sessions with explicit confirmation. Supports DOCX and Google Docs. Write compare_documents Compare two DOCX documents and produce a tracked-changes output document. Provide original_file_path + revi... Write format_layout Apply layout controls (paragraph spacing, table row height, cell padding). Google Docs supports paragraph s... Write init_plan Initialize revision-bound context metadata for coordinated multi-agent planning. Write insert_paragraph Insert a paragraph before/after an anchor paragraph by _bk_* id. Supports DOCX and Google Docs. Write merge_plans Deterministically merge multiple sub-agent plans and detect hard conflicts before apply. Write replace_text Replace text in a paragraph by _bk_* id, preserving formatting. Supports DOCX and Google Docs. Write save Save document. For DOCX: saves clean and/or tracked changes output. For Google Docs: checkpoint (default) r... Write update_footnote Update the text content of an existing footnote.

The managed route: connect Safe Docx through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @usejunior/safe-docx
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? +

Route the Safe Docx server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the 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.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.