Che MCP Server

Swift-native MCP server for Word (.docx) manipulation with 148 tools

Local serverstdioPython

What is the Che MCP server?

Che MCP server exists for a simple reason — assistants are far more useful when they can act on Che directly instead of describing what you should do. Swift-native MCP server for Word (.docx) manipulation with 148 tools.

What you get

A Swift-native MCP (Model Context Protocol) server for Microsoft Word document (.docx) manipulation. This is the first Swift OOXML library that directly manipulates Office Open XML without any third-party Word dependencies.

  • Pure Swift Implementation — No Node.js, Python, or external runtime required
  • Direct OOXML Manipulation — Works directly with XML, no Microsoft Word installation needed
  • Single Binary — Just one executable file
  • 234 MCP Tools — Comprehensive document manipulation across documents, tables, hyperlinks, headers, sections, styles, numbering, content controls, comments, footnotes, equations, fields, and Track Changes
  • Office.js OOXML Roadmap P0 = 100% — All eight P0 sub-issues closed (umbrella #43). Surface coverage is now competitive with Office.js for the read/write side of every P0 capability
  • Dual-Mode Access — Direct Mode (read-only, one step via source_path) and Session Mode (full lifecycle via doc_id)

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What the assistant can call

Once Che is connected, these are the calls the assistant has available:

  • Round — trip silent corruption closed (v3.13.5, #56)**: 5 sub-stack-completion rounds (R5 / R5-CONT /
  • Dual — Mode Access**: Direct Mode (read-only, one step via source_path) and Session Mode (full lifecycle via doc_id)
  • Text — Anchor Insertion**: Insert captions / images relative to matched text (after_text / before_text), no pre-search call required
  • Cross-platform — Works on macOS (universal binary x86_64 + arm64 since v3.5.1)
  • Version — Date
  • v3.22.0 — 2026-07-18
  • v3.13.5 — 2026-04-27
  • v3.13.4 — 2026-04-26
  • v3.13.3 — 2026-04-26
  • v3.13.2 — 2026-04-26
  • v3.13.1 — 2026-04-25
  • v3.13.0 — 2026-04-25

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Che.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the che mcp server does with a few real requests.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Che's toolset — Round, Dual, Text and 11 more — is a fair guide to whether it matches your workflow. It is maintained by kiki830621; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
Roundtrip silent corruption closed (v3.13.5, [#56](https://github.com/PsychQuant/che-word-mcp/issues/56))**: 5 sub-stack-completion rounds (R5 / R5-CONT / R5-CONT-2 / R5-CONT-3 / R5-CONT-4) closed 30 findings (16 P0 + 21 P1)
DualMode Access**: Direct Mode (read-only, one step via source_path) and Session Mode (full lifecycle via doc_id)
TextAnchor Insertion**: Insert captions / images relative to matched text (after_text / before_text), no pre-search call required
Cross-platformWorks on macOS (universal binary x86_64 + arm64 since v3.5.1)
VersionDate
v3.22.02026-07-18
v3.13.52026-04-27
v3.13.42026-04-26
v3.13.32026-04-26
v3.13.22026-04-26
v3.13.12026-04-25
v3.13.02026-04-25
v3.12.02026-04-25
v3.11.02026-04-25

Example prompts to try

  • Use Che to Round.
  • Use Che to Dual.
  • Use Che to Text.

Frequently asked questions

It connects Che to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Round, Dual, Text, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Che directly.