Excalidraw MCP Server logo

Excalidraw MCP Server

by yctimlin

The Excalidraw MCP Server is a Model Context Protocol server that allows Large Language Models (LLMs) to interact with Excalidraw diagrams. It provides a developer-friendly API for creating, modifying, querying, and manipulating Excalidraw drawings.

View on GitHub

Last updated: N/A

What is Excalidraw MCP Server?

The Excalidraw MCP Server is a comprehensive server that enables seamless interaction between Large Language Models (LLMs) and Excalidraw diagrams. It provides an API to create, modify, query, and manipulate Excalidraw drawings.

How to use Excalidraw MCP Server?

The server can be used by sending API requests to create, update, delete, and query Excalidraw elements. It integrates with platforms like Claude Desktop and Cursor by configuring the 'mcpServers' section. Installation can be done via NPM or Docker.

Key features of Excalidraw MCP Server

  • Full Excalidraw Element Control

  • Advanced Element Manipulation

  • Resource Management

  • Easy Integration

Use cases of Excalidraw MCP Server

  • Creating diagrams programmatically with LLMs

  • Modifying existing diagrams based on LLM input

  • Querying diagram elements for information extraction

  • Automating diagram creation and manipulation workflows

FAQ from Excalidraw MCP Server

How do I create a new element?

Use the 'create_element' API call with the required 'type', 'x', and 'y' coordinates, and optional dimensions, colors, and styling properties.

How do I update an existing element?

Use the 'update_element' API call with the required 'id' of the element and any element property to modify.

How do I group multiple elements?

Use the 'group_elements' API call with an array of 'elementIds' to group.

How do I integrate with Claude Desktop?

Add the server configuration to the 'mcpServers' section of your 'claude_desktop_config.json' file.

How do I install the server?

You can install the server using NPM with 'npm install' and 'npm start', or using Docker with 'docker build' and 'docker run'.