word-mcp

word-mcp is a skill for Claude Code, Codex from trsdn/mcp-server-word. It costs 121 tokens per session (1,707 once invoked), scanned A, original, MIT.

Instructions for controlling Microsoft Word on Windows through an MCP server. They cover creating, reading, editing, formatting, reviewing, and rendering Word documents.

In plain words
What is it for?
Working with document text, tables, images, styles, headers, footers, contents pages, comments, tracked changes, bookmarks, footnotes, and form controls.
Why use it?
They explain the required session sequence and Word-specific rules, reducing the risk of leaving files locked or changes unsaved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Working with document text, tables, images, styles, headers, footers, contents pages, comments, tracked changes, bookmarks, footnotes, and form controls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/trsdn/mcp-server-word/word-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add trsdn/mcp-server-word --skill word-mcp
Clone the repo
git clone --depth 1 https://github.com/trsdn/mcp-server-word

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for word-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/trsdn/mcp-server-word/word-mcp/github.svg)](https://agentmods.dev/skills/trsdn/mcp-server-word/word-mcp)
Your own site
<a href="https://agentmods.dev/skills/trsdn/mcp-server-word/word-mcp"><img src="https://agentmods.dev/badge/skills/trsdn/mcp-server-word/word-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for word-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/trsdn/mcp-server-word/word-mcp"><img src="https://agentmods.dev/badge/skills/trsdn/mcp-server-word/word-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.01707
Opus 5 $0.00060 $0.00853
Sonnet 5 $0.00024 $0.00341
Haiku 4.5 $0.00012 $0.00171

Measured 9d ago against content hash 4f39956bab09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

word-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/word-mcp/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Word MCP Server Skill

Seventeen tools, each taking an action parameter. The tool descriptions are complete; this file covers the workflow, the ordering rules that are not obvious, and the places where Word behaves in a way nobody would guess.

Preconditions

  • Windows with Microsoft Word 2016 or newer, desktop edition. The Microsoft Store version cannot be automated.
  • Absolute paths only: C:\Users\me\Documents\report.docx.
  • The document must not already be open in Word. Ask the user to close it rather than guessing.
  • Word runs invisibly and is shut down with the session.

The one rule that matters

Everything runs inside a session. file(open) or file(create) returns a session_id that every other call needs, and file(close) is what actually writes the document and releases Word.

file(open|create) → session_id → edit → file(save) → file(close, save: true)

A session left open holds a WINWORD.EXE process and an exclusive lock on the file. Close it even when the work failed halfway through.

Building a document

Order matters more than it looks:

  1. file(create) — an empty document.
  2. Content first: paragraph(add) with style: "Heading 1" for structure, text(append), table(create), image(insert).
  3. Formatting second: style(create|modify), list(apply), paragraph(set-alignment).
  4. Page setup: section(page-setup), then header-footer(set), then field(insert-page-number).
  5. Fields last: field(insert-toc) then field(update-all). A table of contents inserted before the headings exist stays empty.
  6. file(close, save: true).

Reading a document

  • document(get-info) for the counts, paragraph(list) for the structure. Start there rather than pulling the entire text with text(get).
  • text(find) returns character positions that text(format) and text(get) accept.
  • screenshot(page) answers layout questions — does the table fit, where does the page break, is the header on the right page — far more reliably than any measurement.

Read the full file on GitHub · 154 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 154 lines · 121 tokens per session scan A 4f39956bab09

Subscribe to this mod's changes

word-mcp is a skill published in the GitHub repository trsdn/mcp-server-word (1 stars, last pushed 8d ago), licensed MIT. It adds 121 tokens to every session and 1,707 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

overleaf-sync

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens