Dolibarr MCP Server
Provides structured access to Dolibarr ERP/CRM API endpoints via the Model Context Protocol, supporting CRUD operations on resources like thirdparties, products, and orders.
README
Dolibarr MCP Server
A compliant Model Context Protocol (MCP) server that provides structured access to Dolibarr ERP/CRM API endpoints. Built with Nitro and implementing the JSON-RPC 2.0 specification.
Features
- ✅ MCP Compliant: Full implementation of the Model Context Protocol specification
- 🔧 Complete CRUD Operations: GET, POST, PUT, DELETE support for all Dolibarr endpoints
- 🚀 Production Ready: Built with Nitro for optimal performance and deployment flexibility
- 🔒 Secure: Environment-based configuration with API key authentication
- 📦 Easy Integration: Compatible with n8n, Claude, and other MCP clients
- 🌍 Multi-runtime: Supports Node.js, Bun, and Deno
Quick Start
Prerequisites
- Node.js 18+
- pnpm 9.0+
- Dolibarr instance with REST API enabled
- Valid Dolibarr API key
Installation
# Clone the repository
git clone https://github.com/ivanmartin33/dolibarr-mcp-server.git
cd dolibarr-mcp-server
# Install dependencies
pnpm install
# Copy environment file
cp .env.example .env
# Edit .env with your Dolibarr configuration
# Start development server
pnpm run dev
Environment Setup
Create a .env file in your project root:
DOLI_URL=https://your-dolibarr-instance.com/api/index.php
DOLI_KEY=your-dolibarr-api-key
Running the Server
# Development
pnpm run dev
# Production build
pnpm run build
# Start production server
pnpm run start
The server will be available at http://localhost:3000
MCP Tools Available
The server exposes four main tools for interacting with Dolibarr:
1. dolibarr_get
Fetch data from Dolibarr API using GET method.
{
"name": "dolibarr_get",
"arguments": {
"endpoint": "thirdparties",
"id": "1",
"params": {
"limit": "10"
}
}
}
2. dolibarr_post
Create new data in Dolibarr API using POST method.
{
"name": "dolibarr_post",
"arguments": {
"endpoint": "thirdparties",
"data": {
"name": "New Company",
"client": 1
}
}
}
3. dolibarr_put
Update existing data in Dolibarr API using PUT method.
{
"name": "dolibarr_put",
"arguments": {
"endpoint": "thirdparties",
"id": "1",
"data": {
"name": "Updated Company Name"
}
}
}
4. dolibarr_delete
Delete data from Dolibarr API using DELETE method.
{
"name": "dolibarr_delete",
"arguments": {
"endpoint": "thirdparties",
"id": "1"
}
}
API Endpoints
Main MCP Endpoint
POST /mcp- Main JSON-RPC 2.0 endpoint for MCP communication
Additional Endpoints
GET /mcp/describe- Server information and tool descriptionsPOST /mcp/tools/call- Direct tool execution endpointGET /- Landing page with server information
MCP Protocol Examples
Initialize Connection
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"method": "initialize",
"params": {},
"id": 1
}'
List Available Tools
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"method": "tools/list",
"params": {},
"id": 2
}'
Execute a Tool
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "dolibarr_get",
"arguments": {
"endpoint": "users"
}
},
"id": 3
}'
Integration with n8n
The Dolibarr MCP Server can be easily integrated with n8n for workflow automation:
Connection URLs
- n8n in Docker:
http://host.docker.internal:3000/mcp - Local n8n:
http://localhost:3000/mcp
Starting Server for Docker Access
NITRO_HOST=0.0.0.0 NITRO_PORT=3000 pnpm run dev
HTTP Request Node Configuration
In your n8n workflow, add an HTTP Request node:
- Method: POST
- URL:
http://host.docker.internal:3000/mcp(for Docker) orhttp://localhost:3000/mcp(local) - Headers:
{ "Content-Type": "application/json" } - Body:
{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "dolibarr_get", "arguments": { "endpoint": "{{ $json.endpoint }}", "id": "{{ $json.id }}" } }, "id": "{{ $runIndex }}" }
Dolibarr Configuration
API Setup in Dolibarr
-
Enable REST API Module:
- Go to
Home > Setup > Modules/Applications - Activate "Web services REST API"
- Go to
-
Create API User:
- Go to
Users & Groups - Create a new user or select existing
- Generate API key in user profile
- Go to
-
Set Permissions:
- Assign appropriate permissions to the API user
- Recommended: Create dedicated API user with minimal required rights
Common Dolibarr Endpoints
users- User managementthirdparties- Companies/customersproducts- Product catalogorders- Sales ordersinvoices- Customer invoicesproposals- Commercial proposalscontracts- Contractsprojects- Project management
Production Deployment
Environment Variables
| Variable | Description | Default |
|---|---|---|
NITRO_DOLI_URL |
Dolibarr API base URL | http://localhost/api/index.php |
NITRO_DOLI_KEY |
Dolibarr API key | super_api_key |
NITRO_HOST |
Server host | localhost |
NITRO_PORT |
Server port | 3000 |
Docker
FROM node:18-alpine
# Enable corepack for pnpm
RUN corepack enable
WORKDIR /app
COPY package.json pnpm-lock.yaml ./
RUN pnpm install --frozen-lockfile --prod
COPY . .
RUN pnpm run build
ENV NITRO_HOST=0.0.0.0
ENV NITRO_PORT=3000
EXPOSE 3000
CMD ["node", ".output/server/index.mjs"]
Docker Compose
version: '3.8'
services:
dolibarr-mcp:
build: .
ports:
- "3000:3000"
environment:
- DOLI_URL=http://host.docker.internal:4000/api/index.php
- DOLI_KEY=your-api-key
- NITRO_HOST=0.0.0.0
- NITRO_PORT=3000
restart: unless-stopped
License
This project is licensed under the MIT License - see the LICENSE file for details.
Links
推荐服务器
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。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。