Cloudflare D1 Database MCP Server
Enables interaction with Cloudflare D1 databases through natural language by providing tools to list tables and execute SQL queries. Uses Cloudflare's REST API for lightweight database operations without requiring direct database connections.
README
Cloudflare SYWO MCP Server
A minimal Model Context Protocol (MCP) server that lets MCP-compatible clients query a Cloudflare D1 database. Designed for easy setup and usage.
Features
- List tables in the target D1 database with the
d1_list_tablestool. - Run arbitrary SQL queries using the
d1_querytool. - Lightweight TypeScript implementation relying on Cloudflare's REST API.
- Cross-platform support with proper Windows, macOS, and Linux compatibility.
- Secure credential management via environment variables.
Prerequisites
- Node.js 18+
- Cloudflare Account ID
- Cloudflare D1 Database ID
- Cloudflare D1 Database Name
- Cloudflare API Token with
D1:Editpermissions
Quick Start (5 Minutes)
-
Install the server:
npm install -g cloudflare-sywo-mcp-server -
Get your Cloudflare credentials (takes 2 minutes):
- Account ID: Cloudflare Dashboard → Right sidebar
- Database ID: Cloudflare Dashboard → D1 → Your database → "Database ID"
- Database Name: The name you gave your D1 database
- API Token: Cloudflare Dashboard → My Profile → API Tokens → Create Token → Custom token with
D1:Editpermission
-
Add to VS Code (copy-paste into settings.json):
{ "mcp.servers": { "cloudflare-d1": { "command": "cloudflare-sywo-mcp", "args": ["--stdio"], "env": { "CLOUDFLARE_ACCOUNT_ID": "your-account-id-here", "CLOUDFLARE_D1_DATABASE_ID": "your-database-id-here", "CLOUDFLARE_D1_DATABASE_NAME": "your-database-name-here", "CLOUDFLARE_API_TOKEN": "your-api-token-here" } } } } -
Restart VS Code and you're done!
Installation
npm install -g cloudflare-sywo-mcp-server
Setup
Option 1: Global Installation (Recommended)
After installing globally with npm install -g cloudflare-sywo-mcp-server, you can use it directly in your MCP configuration.
Option 2: Local Development/Custom Build
If you want to build from source or modify the server:
-
Clone or download this repository
-
Install dependencies:
npm install -
Create a
.envfile (do not commit it) and provide credentials:CLOUDFLARE_ACCOUNT_ID=your-account-id-here CLOUDFLARE_D1_DATABASE_ID=your-database-id-here CLOUDFLARE_D1_DATABASE_NAME=your-database-name-here CLOUDFLARE_API_TOKEN=your-api-token-here -
Build the TypeScript project:
npm run build -
Start the MCP server:
npm startOr use the development runner:
npm run dev
MCP Client Configuration
VS Code Setup (Step-by-Step)
For VS Code users, here's exactly what to do:
-
Install the MCP server globally:
npm install -g cloudflare-sywo-mcp-server -
Find your VS Code MCP settings file:
- Open VS Code Command Palette (
Ctrl+Shift+PorCmd+Shift+P) - Type "Open User Settings (JSON)"
- Look for or create the file:
%APPDATA%\Code\User\settings.json(Windows) or~/.config/Code/User/settings.json(Mac/Linux)
- Open VS Code Command Palette (
-
Add the MCP configuration to your settings.json:
Option A: Direct Environment Variables (Recommended)
{ "mcp.servers": { "cloudflare-d1": { "command": "cloudflare-sywo-mcp", "args": ["--stdio"], "env": { "CLOUDFLARE_ACCOUNT_ID": "your-actual-account-id", "CLOUDFLARE_D1_DATABASE_ID": "your-actual-database-id", "CLOUDFLARE_D1_DATABASE_NAME": "your-actual-database-name", "CLOUDFLARE_API_TOKEN": "your-actual-api-token" } } } }Option B: Using .env File
{ "mcp.servers": { "cloudflare-d1": { "command": "cloudflare-sywo-mcp", "args": ["--stdio"], "cwd": "C:/path/to/your/project/folder" } } } -
Where to get your Cloudflare credentials:
- Account ID: Cloudflare Dashboard → Right sidebar under "Account ID"
- Database ID: Cloudflare Dashboard → D1 → Your database → "Database ID"
- Database Name: The name you gave your D1 database
- API Token: Cloudflare Dashboard → My Profile → API Tokens → Create Token → Use "Custom token" with
D1:Editpermission
-
No additional files needed! The credentials go directly in the VS Code settings.json file or in a .env file if you choose that option.
Cursor / Trae Configuration
Add this to your MCP configuration file:
{
"mcpServers": {
"cloudflare-d1": {
"command": "cloudflare-sywo-mcp",
"args": ["--stdio"],
"env": {
"CLOUDFLARE_ACCOUNT_ID": "your-account-id-here",
"CLOUDFLARE_D1_DATABASE_ID": "your-database-id-here",
"CLOUDFLARE_D1_DATABASE_NAME": "your-database-name-here",
"CLOUDFLARE_API_TOKEN": "your-api-token-here"
}
}
}
}
Windows Command Line Configuration
For Windows users, you may need to use the full command path or cmd syntax:
{
"mcpServers": {
"cloudflare-d1": {
"command": "cmd",
"args": ["/c", "set CLOUDFLARE_ACCOUNT_ID=your-account-id-here && set CLOUDFLARE_D1_DATABASE_ID=your-database-id-here && set CLOUDFLARE_D1_DATABASE_NAME=your-database-name-here && set CLOUDFLARE_API_TOKEN=your-api-token-here && cloudflare-sywo-mcp --stdio"]
}
}
}
Alternative: Using .env File
You can also use a .env file in your project directory:
{
"mcpServers": {
"cloudflare-d1": {
"command": "cloudflare-sywo-mcp",
"args": ["--stdio"],
"cwd": "/path/to/your/project"
}
}
}
Make sure to keep your API token secret and rotate immediately if it is ever exposed.
Credential Management Options
Option 1: Direct Environment Variables (Recommended for VS Code)
Put credentials directly in your MCP configuration file. This is the simplest approach.
Option 2: .env File (Good for Development)
Create a .env file in your project directory:
CLOUDFLARE_ACCOUNT_ID=your-account-id-here
CLOUDFLARE_D1_DATABASE_ID=your-database-id-here
CLOUDFLARE_D1_DATABASE_NAME=your-database-name-here
CLOUDFLARE_API_TOKEN=your-api-token-here
Then reference the directory in your MCP config:
{
"mcpServers": {
"cloudflare-d1": {
"command": "cloudflare-sywo-mcp",
"args": ["--stdio"],
"cwd": "/path/to/your/project"
}
}
}
Option 3: System Environment Variables (Advanced)
Set the variables in your system environment, then use a minimal MCP config:
{
"mcpServers": {
"cloudflare-d1": {
"command": "cloudflare-sywo-mcp",
"args": ["--stdio"]
}
}
}
Windows: Set via System Properties → Environment Variables
macOS/Linux: Add to ~/.bashrc or ~/.zshrc:
export CLOUDFLARE_ACCOUNT_ID="your-account-id-here"
export CLOUDFLARE_D1_DATABASE_ID="your-database-id-here"
export CLOUDFLARE_D1_DATABASE_NAME="your-database-name-here"
export CLOUDFLARE_API_TOKEN="your-api-token-here"
Tools Summary
- d1_list_tables: Returns an array of table names from the database.
- d1_query: Executes a SQL query and returns the raw D1 response payload.
Troubleshooting
Connection Issues
If you encounter "Connection closed" errors:
- Ensure all required environment variables are set correctly
- Check that your Cloudflare API token has the necessary permissions (
D1:Edit) - Verify your account ID, database ID, and database name are correct
Windows-Specific Issues
If you see "Syntax Error" from Windows Script Host or "how do I want to open this" popups:
- Make sure you're using version 1.0.7 or later (we fixed Windows compatibility issues)
- Use the Windows command line configuration shown above
- Ensure Node.js is properly installed and in your PATH
JSON Parsing Errors
If you see "Unexpected token" JSON parsing errors:
- Update to the latest version (1.0.7+) which suppresses debug output
- Check that no other processes are writing to stdout/stderr
Security Note
Never commit API tokens to source control. If a token becomes exposed, revoke it in the Cloudflare dashboard and create a fresh one.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.