What is libre-office-mcp AGENTS.md?

Repository instructions for contributors and coding agents working on libre-office-mcp, a server that lets AI assistants create and edit LibreOffice documents.

They are for understanding the project, adding tools, and following its Docker, Python, and document-editing rules.

They explain the repository's layout, architecture, supported tools, and constraints before someone changes the code.

How harshithb3304/libre-office-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to harshithb3304/libre-office-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/harshithb3304/libre-office-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/harshithb3304/libre-office-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/harshithb3304/libre-office-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/harshithb3304/libre-office-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/harshithb3304/libre-office-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/harshithb3304/libre-office-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/harshithb3304/libre-office-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/harshithb3304/libre-office-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,635 This file is loaded in full into every session.

When invoked 1,635 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01635	$0.01635
Opus 5.5	$0.00654	$0.00654
Sonnet 5.5	$0.00327	$0.00327
Haiku 4.5	$0.00163	$0.00163

Measured 14d ago against content hash 3394084143d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

libre-office-mcp AGENTS.md 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 14d 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.

AGENTS.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — guide for AI coding agents and new contributors

An MCP server that lets AI assistants create and edit documents with LibreOffice. Implemented: Writer (55 tools), Calc (51), Impress (42) and core office_* tools (8). Humans: start with README.md; this file is a map of what is where and the rules that are easy to break.

The architecture in 5 lines

AI client ──MCP (stdio | http)──▶ server (normal Python, `mcp` SDK v2)
                                    │  one JSON object per line on stdin/stdout
                                    ▼
                                  worker (LibreOffice's own Python: stdlib + `uno` only)
                                    │  UNO over a private named pipe
                                    ▼
                                  soffice --headless

Two Python programs because only LibreOffice's Python can import uno (see docs/ARCHITECTURE.md).
One request at a time (an asyncio.Lock in client.py). No pool, no sessions.
Every edit = copy file to scratch → edit the copy → atomically replace the original. A batch is all-or-nothing.
Docker is the only supported way to run it (Dockerfile, docker-compose.yml). The code assumes Linux (the image's Ubuntu); there is no Windows/macOS-specific code.

Where things are

You want to…	Look in
add/change what the AI sees (tool name, params, description)	`src/libreoffice_mcp/tools/<app>/`
add/change the LibreOffice logic (UNO calls)	`src/libreoffice_mcp/worker/ops/<app>/`
change how requests run (open → ops → save)	`worker/runner.py`, `worker/session.py`
change process start/stop, crash handling, timeouts	`client.py` (server side), `worker/office.py` + `worker/main.py`
change flags / env vars	`config.py`
change HTTP mode (health, host check)	`http_server.py`
change path rules / `--root` sandbox	`paths.py`
change what the AI is told on connect	`INSTRUCTIONS` in `app.py`
supported file types and LibreOffice filter names	`formats.py`
find LibreOffice / its Python	`locate.py`
container image	`Dockerfile`, `docker-compose.yml`

Read the full file on GitHub · 113 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.

14d ago First seen · 113 lines · 1,635 tokens per session scan A 3394084143d5

Subscribe to this mod's changes

libre-office-mcp AGENTS.md is an instructions file published in the GitHub repository harshithb3304/libre-office-mcp (17 stars, last pushed 14d ago), licensed MIT. It adds 1,635 tokens to every session, about $0.0065 per session on Opus 5.5. 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 2026-10-24.

Building agents Documents libreoffice libreoffice-calc libreoffice-impress libreoffice-writer mcp mcp-server

libre-office-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
libre-office-mcp AGENTS.mdharshithb3304/libre-office-mcp	Instructions file	17	14d ago	MIT	A	1,635	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

libre-office-mcp: Instructions file for Codex