MCP Mermaid ER Server
Parses Mermaid ER diagrams to create PostgreSQL tables and automatically generates REST and GraphQL CRUD APIs.
README
MCP Mermaid ER Server
An open-source Model Context Protocol (MCP) server that parses Mermaid ER diagrams, creates PostgreSQL database tables, and exposes automatic REST/GraphQL CRUD APIs.
Features
- 🔍 Parse Mermaid ER Diagrams - Extract entities, attributes, and relationships
- 🗄️ Auto-Create PostgreSQL Tables - Generate DDL and execute against your database
- 🚀 REST API Generation - Automatic CRUD endpoints for all entities
- 📊 GraphQL API Generation - Type-safe queries and mutations
- 🔑 Key Detection - Identifies PK, FK, and UK constraints
- ⚙️ Configurable - Environment variables for database and API settings
Installation
git clone https://github.com/yourusername/mcp-mermaid-er-server.git
cd mcp-mermaid-er-server
npm install
npm run build
Configuration
Create a .env file (copy from .env.example):
# Mermaid Source
MERMAID_DIAGRAM_PATH=./examples/sample-er.mmd
# Database (PostgreSQL)
DB_HOST=localhost
DB_PORT=5432
DB_NAME=mydb
DB_USER=postgres
DB_PASSWORD=password
# API Server
API_TYPE=rest # rest, graphql, or both
API_PORT=3000
API_HOST=0.0.0.0
Claude Desktop Integration
Add to claude_desktop_config.json:
{
"mcpServers": {
"mermaid-er": {
"command": "node",
"args": ["/path/to/mcp-tools/dist/index.js"],
"env": {
"MERMAID_DIAGRAM_PATH": "/path/to/your/diagram.mmd",
"DB_HOST": "localhost",
"DB_NAME": "mydb",
"DB_USER": "postgres",
"DB_PASSWORD": "password"
}
}
}
}
Available MCP Tools (12 Total)
Parsing Tools
| Tool | Description |
|---|---|
parse_er_diagram |
Parse ER diagram, return full schema |
list_entities |
List all entity names |
get_entity_details |
Get attributes for an entity |
get_relationships |
Get all relationships |
validate_diagram |
Validate diagram syntax |
Database Tools
| Tool | Description |
|---|---|
test_connection |
Test PostgreSQL connection |
generate_sql |
Generate DDL without executing |
create_schema |
Create tables in database |
drop_schema |
Drop all tables (requires confirmation) |
API Tools
| Tool | Description |
|---|---|
start_api_server |
Start REST/GraphQL server |
stop_api_server |
Stop the API server |
get_api_endpoints |
List all endpoints |
Workflow Example
- Parse your ER diagram →
parse_er_diagram - Review the SQL →
generate_sql - Create database tables →
create_schema - Start the API server →
start_api_server - Use the auto-generated endpoints!
API Endpoints
REST (when API_TYPE=rest or both)
GET /api/{entity} - List all records
GET /api/{entity}/:id - Get by ID
POST /api/{entity} - Create record
PUT /api/{entity}/:id - Update record
DELETE /api/{entity}/:id - Delete record
GraphQL (when API_TYPE=graphql or both)
# Queries
query { customers { customer_id email } }
query { customer(id: "1") { email } }
# Mutations
mutation { createCustomer(input: { email: "test@example.com" }) { customer_id } }
mutation { updateCustomer(id: "1", input: { email: "new@example.com" }) { email } }
mutation { deleteCustomer(id: "1") { customer_id } }
Supported ER Syntax
erDiagram
CUSTOMER {
int customer_id PK "Primary key"
string email UK "Unique email"
string name
}
ORDER {
int order_id PK
int customer_id FK
datetime order_date
}
CUSTOMER ||--o{ ORDER : "places"
Development
npm run dev # Run with ts-node
npm run build # Compile TypeScript
npm test # Run tests
License
MIT License - see LICENSE
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。