dolibarr-mcp/README.md

Dolibarr MCP Server

Dolibarr MCP is a focused Model Context Protocol (MCP) server that exposes the most useful Dolibarr ERP/CRM operations to AI copilots.

This MCP server enables complete management of your Dolibarr ERP/CRM through AI tools such as Claude Desktop. With specialised tools you can manage customers, products, invoices, orders, contacts, and system administration tasks from a single MCP endpoint.

📚 Documentation

All user and contributor guides live in docs/:

• Quickstart – installation and first run instructions for Linux, macOS, and Windows
• Configuration – environment variables and secrets consumed by the server
• Development – test workflow, linting, and Docker helpers
• API Reference – Dolibarr REST resources and corresponding MCP tools

✨ Features

• 💼 Complete ERP/CRM Management – Tools for customers, products, invoices, orders, and contacts
• ⚡ Async/Await Architecture – Modern, high-performance HTTP client and server
• 🛡️ Comprehensive Error Handling – Robust validation and structured responses
• 🐳 Docker Support – Optional container workflow for local experimentation and deployment
• 🔧 Production-Ready – Automated tests and configuration management powered by pydantic-settings

🛠 Available tools

dolibarr_mcp_server registers MCP tools that map to common Dolibarr workflows. See the API reference for full details.

• System – test_connection, get_status, and dolibarr_raw_api
• Users – CRUD helpers for Dolibarr users
• Customers / Third Parties – CRUD helpers for partners
• Products – CRUD helpers for product catalogue entries
• Invoices – CRUD helpers for invoices
• Orders – CRUD helpers for customer orders
• Contacts – CRUD helpers for contact records

The async implementation in dolibarr_client.py handles authentication, pagination, and error handling for all endpoints.

📦 Installation

Linux / macOS

git clone https://github.com/latinogino/dolibarr-mcp.git
cd dolibarr-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

Install development extras (pytest, formatting, type-checking) when needed:

pip install -e '.[dev]'

Windows (Visual Studio vsenv)

1. Launch the x64 Native Tools Command Prompt for VS or Developer PowerShell for VS (vsenv).
2. Create a virtual environment: py -3 -m venv .venv.
3. Activate it: call .venv\\Scripts\\activate.bat (Command Prompt) or .\\.venv\\Scripts\\Activate.ps1 (PowerShell).
4. Install the package: pip install -e ..
5. Install development extras when required: pip install -e .[dev] (PowerShell requires escaping brackets: pip install -e .`[dev`]).
6. Note the Python path (where python) for integration with Claude Desktop or other MCP hosts.

Docker

# Using Docker Compose (recommended)
docker compose up -d

# Or build and run directly
docker build -t dolibarr-mcp .
docker run -d \
  -e DOLIBARR_URL=https://your-dolibarr.example.com/api/index.php \
  -e DOLIBARR_API_KEY=YOUR_API_KEY \
  dolibarr-mcp

⚙️ Configuration

Set the following environment variables (they may live in a .env file):

• DOLIBARR_URL – Dolibarr API endpoint, e.g. https://example.com/api/index.php
• DOLIBARR_API_KEY – personal Dolibarr API token
• LOG_LEVEL – optional logging verbosity (defaults to INFO)

Config is built with pydantic-settings and supports loading from the environment, .env files, and CLI overrides. See the configuration guide for a full matrix and troubleshooting tips.

▶️ Running the server

Dolibarr MCP communicates with hosts over STDIO. Once configured, launch the server with:

python -m dolibarr_mcp.cli serve

You can validate credentials and connectivity using the built-in test command before wiring it into a host:

python -m dolibarr_mcp.cli test --url https://example.com/api/index.php --api-key YOUR_TOKEN

🤖 Using with Claude Desktop

Add an entry to claude_desktop_config.json that points to your virtual environment’s Python executable and the dolibarr_mcp.cli module. After installation, verify the executable path with which python (Linux/macOS) or where python (Windows vsenv). Restart Claude Desktop so it picks up the new MCP server.

🧪 Development workflow

• Run the test-suite with pytest (see development docs for coverage flags and Docker helpers).
• Editable installs rely on the src/ layout and expose the dolibarr-mcp console entry point.
• Contributions follow the same structure and documentation conventions as prestashop-mcp to keep the twin projects in sync.

📄 License

=======

python -m dolibarr_mcp.cli test --url https://your-dolibarr.example.com/api/index.php --api-key YOUR_KEY

Available tools

• System – test_connection, get_status
• Users – get_users, get_user_by_id, create_user, update_user, delete_user
• Customers / Third parties – get_customers, get_customer_by_id, create_customer, update_customer, delete_customer
• Products – get_products, get_product_by_id, create_product, update_product, delete_product
• Invoices – get_invoices, get_invoice_by_id, create_invoice, update_invoice, delete_invoice
• Orders – get_orders, get_order_by_id, create_order, update_order, delete_order
• Contacts – get_contacts, get_contact_by_id, create_contact, update_contact, delete_contact
• Raw API access – dolibarr_raw_api

License

This project is released under the MIT License.