Sponsored by Deepsite.site

Boomi MCP Server

Created By
Glebuar7 months ago
An MCP server for interaction with the Boomi API.
Content

Boomi MCP Server

CI Docker License

This repository provides a simple Model Context Protocol (MCP) server for interacting with the Boomi API. The server exposes Boomi SDK operations as MCP tools using FastMCP.

Table of Contents

Requirements

  • Python 3.10+
  • Access credentials for the Boomi API

Quick start

The recommended way to run the Boomi MCP Server is using Docker:

# Pull the latest image
docker pull ghcr.io/glebuar/boomi-mcp-server:latest

# Run with environment variables
docker run -d --name boomi-mcp-server -p 8080:8080 \
  -e BOOMI_ACCOUNT=your_account \
  -e BOOMI_USER=your_user \
  -e BOOMI_SECRET=your_secret \
  ghcr.io/glebuar/boomi-mcp-server:latest

Alternatively, you can build from source:

git clone https://github.com/glebuar/boomi-mcp-server.git
cd boomi-mcp-server
docker build -t boomi-mcp-server .
docker run -p 8080:8080 --env-file .env boomi-mcp-server

Usage

Set your Boomi credentials using environment variables or a .env file (copy the provided .env.example and fill in your values):

BOOMI_ACCOUNT=...
BOOMI_USER=...
BOOMI_SECRET=...

If a .env file exists in the working directory the server will load it automatically.

Using the Python client

A Python client is available in the src/boomi_mcp_client directory for programmatic access:

import sys
sys.path.append('src')
from boomi_mcp_client import MCPClient

client = MCPClient("http://localhost:8080")
print(client.list_tools())
result = client.call_tool("health_check")
print(result)

See examples/using_client.py for a complete script demonstrating these calls.

Running via Docker

Docker is the recommended way to run the Boomi MCP Server for production use:

  1. Create a .env file from the example:

    cp .env.example .env
    # Edit .env with your Boomi credentials
    
  2. Start the server:

    docker-compose up -d
    
  3. Check if server is running:

    docker ps | grep boomi-mcp-server
    

Using Docker directly

# Build the image
docker build -t boomi-mcp-server .

# Run with environment variables
docker run -d \
  --name boomi-mcp-server \
  -p 8080:8080 \
  -e BOOMI_ACCOUNT=your_account \
  -e BOOMI_USER=your_user \
  -e BOOMI_SECRET=your_secret \
  boomi-mcp-server

# Or use an env file
docker run -d \
  --name boomi-mcp-server \
  -p 8080:8080 \
  --env-file .env \
  boomi-mcp-server

Docker Features

  • Non-root user: Runs as unprivileged user for security
  • Health checks: Built-in health monitoring
  • Optimized layers: Efficient caching for faster rebuilds
  • Production ready: Includes all necessary runtime dependencies

Running from Source

For development or when you need to run the server locally without Docker:

Prerequisites

  • Python 3.10+
  • pip or uv package manager

Setup

git clone https://github.com/glebuar/boomi-mcp-server.git
cd boomi-mcp-server

# Create virtual environment
python -m venv .venv
source .venv/bin/activate     # Linux/macOS
# or .venv\Scripts\activate    # Windows

# Install dependencies
pip install -r requirements.txt

Running the server

# stdio mode (for Cursor/Claude Desktop integration)
python -m boomi_mcp_server.server

# SSE mode (HTTP server on port 8080)
python -m boomi_mcp_server.server --transport sse --port 8080

Integration with Claude Desktop

For Claude Desktop integration, add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "boomi": {
      "command": "python",
      "args": [
        "-m",
        "boomi_mcp_server.server"
      ],
      "cwd": "/path/to/boomi-mcp-server",
      "env": {
        "BOOMI_ACCOUNT": "your_account",
        "BOOMI_USER": "your_user",
        "BOOMI_SECRET": "your_secret"
      }
    }
  }
}

Features

The server exposes 85+ tools covering the complete Boomi integration lifecycle:

Core Workflow Support

  • Discovery: Query components, environments, atoms, and folders
  • Development: Create/update components, manage folders
  • Packaging: Create versioned packages for deployment
  • Deployment: Deploy packages, check deployment status
  • Execution: Run processes with parameters, manage attachments
  • Monitoring: Query executions, view logs, track performance
  • Debugging: Access detailed logs, artifacts, and error records
  • Management: Handle schedules, properties, extensions

Connector Support

  • AS2, EDI (X12/EDIFACT), HL7, OFTP2, RosettaNet, Tradacoms
  • Query connector records and retrieve artifacts
  • Manage connector configurations

Advanced Features

  • Process-atom attachments for execution
  • Environment-atom attachments
  • Queue management and listener control
  • Audit logs and system events
  • Document rerun capabilities
  • Runtime restart management

See docs/cursor_setup.md for instructions on setting up the server with Cursor/Claude Desktop.

Development

Running tests

To run tests, you'll need to install development dependencies:

# Clone the repository
git clone https://github.com/glebuar/boomi-mcp-server.git
cd boomi-mcp-server

# Create virtual environment
python -m venv .venv
source .venv/bin/activate

# Install test dependencies
pip install -r requirements.txt
pip install pytest pytest-cov ruff

# Run tests
pytest

# Run linter
ruff check .

Contributing

Please open an issue or pull request if you encounter problems or have improvements. Ensure pytest and ruff pass before submitting changes.

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
ChatWiseThe second fastest AI chatbot™
Playwright McpPlaywright MCP server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
DeepChatYour AI Partner on Desktop
Tavily Mcp
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Serper MCP ServerA Serper MCP Server
WindsurfThe new purpose-built IDE to harness magic
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
CursorThe AI Code Editor
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Amap Maps高德地图官方 MCP Server