Skip to main content

doc-control

doc-control: let AI agents edit Word documents safely. Deterministic .docx edits, every change a tracked change the writer can reject.

Status: file engine working (pre-1.0; the API may still change). The live Word engine is not built yet. See status/specification.md and status/plan.md.

A deterministic tool that lets AI agents work on Word documents quickly, precisely and safely, ideally live in the Word window the writer has open. Every content change is a tracked change the writer can accept or reject.

For anyone — writers and editors first — who wants an AI agent's help inside a Word document without a single silent change.

Usage

Install with pip install doc-control (or run it without installing: uvx doc-control). Python 3.11+, no other dependencies.

Command line, JSON in and JSON out:

doc-control outline --json '{"doc": "Novela.docx"}'
doc-control find --json '{"doc": "Novela.docx", "query": "lluvia"}'
doc-control batch --json '{"doc": "Novela.docx", "ops": [
  {"op": "text.replace", "at": "p12#a7b2a7b2:4-10", "text": "nieve"},
  {"op": "comment.add", "at": "p40#c0ffee00", "text": "¿Seguro?"}]}'
doc-control help batch          # the JSON Schema of any operation

Every write is a tracked change by DOC_CONTROL_AUTHOR (default Claude), made after a backup and verified, with undo and history.* to go back. Addresses like p12#a7b2a7b2 come from read results and fail loudly if the paragraph changed.

From Python, a document can be held open for many reads, with whole results:

from doc_control import api

with api.open("Novela.docx") as doc:
    for p in doc.paragraphs(normalized=True, pages=True):
        print(p["at"], p["style_name"], p["page"], p["text"][:40])
    chapters = doc.run("segment", {"unit": "chapters"})["chapters"]

Recipes propose batches of fixes (Spanish typography, quotes, dashes, spacing, empty paragraphs and more): recipe.list, then recipe.run returns a batch to review and apply.

References: operations · errors.

Planned shape

  • One core, two engines, one API
    • File engine: edits a closed .docx with the Python standard library only, rewriting only the parts it touches. Read operations also take a .txt, .md or .odt file (hard-wrapped text detected; Markdown # headings and OpenDocument headings become Heading styles); writes refuse it.
    • Live engine: controls the open Word (Windows/COM first, Mac later).
  • Two front doors: a CLI with JSON in/out, and an MCP server (doc-control mcp, stdio) for Claude Desktop / Cowork and other MCP clients.
  • Safety first: lock-file and on-disk change detection, backup before every write, verification, automatic restore, operation log with undo, and unintended_changes == 0 as a gate.
  • No AI inside. Judgment belongs to the agent; approval belongs to the writer.

It will replace docx-fixer, whose rules become packs built on this tool, and serve literary-critic as its first downstream consumer.

MCP server

doc-control mcp serves every operation as an MCP tool over stdio, one tool per operation (para.move becomes para_move), with the same JSON Schemas and the same response envelope as the CLI. It needs nothing beyond the package itself:

{
  "mcpServers": {
    "doc-control": { "command": "uvx", "args": ["doc-control", "mcp"] }
  }
}

Documents

Development

This repo uses claude-arsenal (spec-driven workflow, gated tasks in arsenal/tasks/). See CLAUDE.md.

Same author:

  • claude-arsenal — a Claude Code skill and plugin marketplace: specs before code, failing tests first, gates with numbers.
  • literary-critic — lets an LLM index, analyse and advise on a full novel manuscript the way a professional editor would; doc-control's first planned consumer.
  • drawspec — declarative diagram spec → clean, themeable SVG; JSON with no coordinates, so an LLM can write it.
  • integral-job-search — a candidate-centred job search run as a conversation in Claude Code.

License

Apache-2.0

Metadata

Release files for doc-control 0.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for doc-control 0.5.1
File Size Uploaded
doc_control-0.5.1.tar.gz 463.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for doc-control 0.5.1
File Interpreter ABI Platform
doc_control-0.5.1-py3-none-any.whl Python 3 none any Details

Total release size: 759.5 kB

Release files / doc_control-0.5.1.tar.gz

Download URL doc_control-0.5.1.tar.gz
Size 463.2 kB
Tags Source
SHA-256 checksum
How to use checksums
8371aa68c7a95bb2b65a9e9c0085094b2cf5de4b683429d8963b014e910050b9
BLAKE2b-256 checksum
How to use checksums
d8d113239820eebd1a64bc09bb54b8165a585860e3f19187a8682d7d76867950
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 13, 2026.

Transparency log

Release files / doc_control-0.5.1-py3-none-any.whl

Download URL doc_control-0.5.1-py3-none-any.whl
Size 296.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
05be74109a6b32f62ca3f43a1a82daf7debd365609225430ddb719b810b6a60a
BLAKE2b-256 checksum
How to use checksums
814f981bef72a7c0e6fbd1b1873e755196e034d595feabfdb81b5331431629c1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 13, 2026.

Transparency log

Release history Release notifications | RSS feed

0.6.1

2 release files

0.6.0

2 release files

This release

0.5.1 This release

2 release files

0.5.0

2 release files

0.4.1

2 release files

0.4.0

2 release files

0.3.0

2 release files

0.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page