---
title: "Lucid MCP integration for LuumenAI"
url: "https://www.luumen.ai/integrations/lucid-mcp/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Lucid MCP integration for LuumenAI

Read your Lucid diagrams for context, and draft new ones as approved steps.

## What LuumenAI can do with Lucid MCP

LuumenAI connects to Lucid MCP with OAuth 2.0 and exposes 35 tools (13 read-only · 17 write · 5 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: OAuth 2.0
- Tools available: 35 tools (13 read-only · 17 write · 5 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Lucid MCP with LuumenAI

Your architecture lives in Lucid. Luumen reads it: document metadata, folder contents, comment threads, and the text inside a diagram. Ask what a service talks to during an incident and get the answer from the picture your team already maintains. When something needs to change or a new diagram needs to exist, Luumen shows the plan first and waits for your approval. Connected with OAuth via dynamic client registration.

## Example tools

Read-only (13 in total):

- `LUCID_MCP_FETCH` — Retrieves the structured content of a specific Lucid document by its ID.
- `LUCID_MCP_GET_MCP_RESOURCE` — Reads a resource from this MCP server by URI.
- `LUCID_MCP_LIST_DOCUMENT_THREAD_COMMENTS` — List comments on a specific collaboration thread of a Lucid document.
- `LUCID_MCP_LIST_DOCUMENT_THREADS` — List collaboration threads on a Lucid document.
- `LUCID_MCP_LUCID_EXPORT_DOCUMENT_AS_PNG` — Exports a Lucid document page as a PNG image.
- `LUCID_MCP_LUCID_FETCH_ITEM_IMAGE` — Fetches the source image attached to a specific item in a Lucid document.
- `LUCID_MCP_LUCID_GET_DOCUMENT_METADATA` — Get metadata for a Lucid document.
- `LUCID_MCP_LUCID_LIST_FOLDER_CONTENTS` — List the documents and subfolders inside a Lucid folder.

Write and destructive (22 in total, approval required by default):

- `LUCID_MCP_LUCID_ADD_BLOCK` — Add a new block (shape) to a Lucid document.
- `LUCID_MCP_LUCID_ADD_DYNAMIC_TABLE` — Add a dynamic table to a Lucid document.
- `LUCID_MCP_LUCID_ADD_ITEMS_TO_DYNAMIC_TABLE` — Add existing canvas blocks to a dynamic table.
- `LUCID_MCP_LUCID_ADD_LINE` — Add a new line to a Lucid document, connecting two points or shapes.
- `LUCID_MCP_LUCID_CREATE_DIAGRAM_FROM_SPECIFICATION` — Creates a Lucid document using the Standard Import format (.lucid file).
- `LUCID_MCP_LUCID_CREATE_DOCUMENT_SHARE_LINK` — Creates a new share link for a document with specified permissions.
- `LUCID_MCP__LUCID_CREATE_EMBED` — Internal tool for MCP Apps extension only.
- `LUCID_MCP__LUCID_CREATE_EMBED_SESSION_TOKEN` — Internal tool for MCP Apps extension only.

## Frequently asked questions

### How does LuumenAI connect to Lucid MCP?

Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Lucid MCP on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 5 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

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

Full page: https://www.luumen.ai/integrations/lucid-mcp/