---
title: "HackMD integration for LuumenAI"
url: "https://www.luumen.ai/integrations/hackmd/"
entity: SoftwareIntegration
category: "Knowledge & documentation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# HackMD integration for LuumenAI

Read team notes for context, and draft new ones as approved steps

## What LuumenAI can do with HackMD

LuumenAI connects to HackMD with an API token and exposes 8 tools (5 read-only · 2 write · 1 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 8 tools (5 read-only · 2 write · 1 destructive)
- Plan: available on all plans
- Category: Knowledge & documentation

## About HackMD with LuumenAI

Connect HackMD and your runbooks, incident notes, and team docs become context the agent can read directly. Ask what a procedure says, find the folder a postmortem belongs in, or check what is sitting in trash. When the agent writes a note, moves one to trash, or restores one, it shows you the change first and waits for approval.

## Example tools

Read-only (5 in total):

- `HACKMD_GET_ACCOUNT` — Return the HackMD profile for the connected token and the teams visible to it.
- `HACKMD_GET_NOTE` — Get a note by ID, including its Markdown content.
- `HACKMD_LIST_FOLDERS` — List all folders in the personal workspace, or in one team workspace when team_path is supplied.
- `HACKMD_LIST_NOTES` — List all notes in the personal workspace, or in one team workspace when team_path is supplied.
- `HACKMD_LIST_TRASH` — List soft-deleted notes in the personal workspace.

Write and destructive (3 in total, approval required by default):

- `HACKMD_CREATE_NOTE` — Create a Markdown note in the personal workspace or a specified team workspace.
- `HACKMD_MOVE_NOTE_TO_TRASH` — Soft-delete a note by moving it to trash in the personal workspace or an explicitly selected team workspace.
- `HACKMD_RESTORE_NOTES` — Restore one or more personal notes from HackMD trash.

## Frequently asked questions

### How does LuumenAI connect to HackMD?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in HackMD on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to HackMD — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/hackmd/