Eraser.io

v1.0.0Developer Toolsstable

A Python MCP (Model Context Protocol) server and CLI tool to render diagrams using the Eraser API.

code-to-diagramdiagramdiagram-generationdiagrammingdiagramming-as-code
Share:
21
Stars
0
Downloads
0
Weekly
0/5

What is Eraser.io?

Eraser.io is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python mcp (model context protocol) server and cli tool to render diagrams using the eraser api.

A Python MCP (Model Context Protocol) server and CLI tool to render diagrams using the Eraser API.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Python MCP (Model Context Protocol) server and CLI tool to

Use Cases

Create diagrams programmatically using the Eraser API.
Generate architecture and flowchart visualizations from natural language.
buck-0x

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMar 29, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx eraser-io

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Eraser.io

The Eraser.io MCP server is a Python-based Model Context Protocol server and CLI tool that renders professional diagrams (sequence, flowchart, ER, cloud architecture, and more) by sending diagram descriptions to the Eraser API. It integrates with Claude Desktop, VS Code, and Windsurf, allowing AI assistants to produce visual architecture diagrams, system designs, and data-flow charts on demand with natural language prompts. Developers and architects who use Eraser for documentation can automate diagram creation directly inside their AI coding workflow.

Prerequisites

  • Python 3.10 or higher
  • An active Eraser account with an API token (ERASER_API_TOKEN) from eraser.io
  • pip or uv package manager
  • An MCP-compatible client such as Claude Desktop, VS Code with MCP support, or Windsurf
1

Clone the repository

Download the eraser-io-mcp-server source code.

git clone https://github.com/buck-0x/eraser-io-mcp-server.git
cd eraser-io-mcp-server
2

Install Python dependencies

Install the package and its dependencies using pip or uv. The -e flag installs in editable mode so changes take effect immediately.

pip install -e .
# or with uv:
uv pip install -e .
3

Set your Eraser API token

Create a .env file or export the token as an environment variable. The ERASER_API_TOKEN is the only required secret.

cp .env.example .env
# Edit .env:
# ERASER_API_TOKEN=your-eraser-api-token
4

Test the server in STDIO mode

Run the MCP server directly to confirm it starts and is ready to accept connections from an MCP client.

python -m eraser_mcp
5

Add to your MCP client configuration

Register the server in your Claude Desktop or VS Code MCP config file, passing the API token through the env block.

Eraser.io Examples

Client configuration

Claude Desktop configuration for the Eraser.io MCP server using the Python module entry point.

{
  "mcpServers": {
    "eraser-io": {
      "command": "python",
      "args": ["-m", "eraser_mcp"],
      "env": {
        "ERASER_API_TOKEN": "your-eraser-api-token"
      }
    }
  }
}

Prompts to try

Example prompts that use the Eraser.io MCP server to generate diagrams from natural language descriptions.

- "Draw a sequence diagram showing the OAuth2 authorization code flow between client, server, and identity provider"
- "Create a cloud architecture diagram for a three-tier web app on AWS with ALB, ECS, and RDS"
- "Generate an ER diagram for a blog database with users, posts, comments, and tags tables"
- "Make a flowchart showing the CI/CD pipeline from git push to production deployment"
- "Produce a dark-themed architecture diagram of a Kafka event streaming system"

Troubleshooting Eraser.io

403 or 401 error when rendering a diagram

Verify that ERASER_API_TOKEN is set correctly in your environment or .env file. Log into eraser.io and regenerate the API token if necessary.

Icon validation warnings appear in the output

Set the environment variable SKIP_ICON_CHECK=true to suppress warnings about non-standard icon names used in cloud architecture diagrams.

Server starts but Claude Desktop does not list any tools

Confirm the command in your config points to the correct Python interpreter (use 'which python' or specify the full virtualenv path) and that the package was installed in the same environment.

Frequently Asked Questions about Eraser.io

What is Eraser.io?

Eraser.io is a Model Context Protocol (MCP) server that python mcp (model context protocol) server and cli tool to render diagrams using the eraser api. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Eraser.io?

Follow the installation instructions on the Eraser.io GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Eraser.io?

Eraser.io works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Eraser.io free to use?

Yes, Eraser.io is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "eraser-io": { "command": "npx", "args": ["-y", "eraser-io"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Eraser.io?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides