
mcp server edgedb
EdgeDB MCP服务器项目
Repository Info
About This Server
EdgeDB MCP服务器项目
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
@obiwan90/edgedb-mcp-server
EdgeDB MCP Server is a tool based on the Model Context Protocol (MCP) that provides query and management capabilities for EdgeDB databases. It can be used as a command-line tool or integrated as a library into other projects.
Features
-
Database Management Tools
- Connect to databases (supports DSN and instance name)
- List available databases
- Create new databases
- Switch current database
- Get current database information
-
Query Tools
- Execute EdgeQL queries
- Execute EdgeQL queries with parameters
- Find single records
- Find multiple records (with filtering, sorting, pagination)
-
Schema Management Tools
- List types (optionally including system types)
- Get type details
- Compare schema structures
Installation
Temporary Execution (without installation)
npx -y @obiwan90/edgedb-mcp-server@latest
Global Installation
npm install -g @obiwan90/edgedb-mcp-server
As a Project Dependency
npm install @obiwan90/edgedb-mcp-server
Usage
Command Line Usage
# If installed globally
edgedb-mcp-server
# Or via npx for temporary execution
npx -y @obiwan90/edgedb-mcp-server
Integration as a Library
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { registerAllTools } from "@obiwan90/edgedb-mcp-server/build/tools/index.js";
import { registerAllResources } from "@obiwan90/edgedb-mcp-server/build/resources/index.js";
// Initialize MCP server
const server = new McpServer({
transport: new StdioServerTransport(),
name: "EdgeDB MCP Server",
description: "Providing EdgeDB database services through MCP protocol",
version: "1.0.0"
});
// Register resources and tools
registerAllResources(server);
registerAllTools(server);
// Start the server
(async function() {
try {
const transport = new StdioServerTransport();
await server.connect(transport);
console.log("MCP server connected, waiting for client requests...");
} catch (error) {
console.error("Server startup failed:", error);
process.exit(1);
}
})();
Environment Variables
EDGEDB_DSN- EdgeDB database connection stringEDGEDB_INSTANCE- EdgeDB instance nameDEBUG- Enable debug mode (true/false)LOG_LEVEL- Log level (default: info)
Project Development
Directory Structure
src/
├── config/ # Configuration management
├── resources/ # MCP resource definitions
├── services/ # Service layer (EdgeDB connection management)
├── tools/ # MCP tool definitions
│ ├── database.ts # Database management tools
│ ├── query.ts # Query tools
│ ├── schema.ts # Schema management tools
│ └── index.ts # Tool exports
├── types/ # Type definitions
├── utils/ # Utility functions
└── index.ts # Application entry point
Building the Project
# Clone the project
git clone https://github.com/obiwan90/mcp-server-edgedb.git
cd mcp-server-edgedb
# Install dependencies
npm install
# Build the project
npm run build
# Start the service
npm start
Cursor Integration
To integrate this MCP server with the Cursor editor, follow these steps:
- Edit Cursor's MCP configuration file (
~/.cursor/mcp.json) - Add the following configuration:
"edgedb-server": {
"command": "npx",
"args": [
"-y",
"@obiwan90/edgedb-mcp-server@latest"
]
}
"edgedb-server": {
"command": "npx",
"args": [
"-y",
"@obiwan90/edgedb-mcp-server@latest",
"--instanceName",
"your-instance-name"
]
}
- Restart the Cursor editor
- Now you can use EdgeDB tools in Cursor! Access them through the command palette (Cmd+Shift+P) by searching for "EdgeDB" or via the chat interface.
Cursor dialog box input:
mcp_edgedb-server_connectEdgeDB(instanceName="your-instance-name")
License
This project is licensed under the MIT License.
Quick Start
Clone the repository
git clone https://github.com/obiwan90/mcp-server-edgedbInstall dependencies
cd mcp-server-edgedb
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.