- Home
- MCP servers
- MCP Database Server
MCP Database Server
- typescript
1
GitHub Stars
typescript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"juanyin1-mcp-database-server-with-database": {
"command": "npx",
"args": [
"-y",
"@executeautomation/database-server",
"/path/to/your/database.db"
]
}
}
}You can connect Claude to multiple databases using this MCP server, giving Claude the ability to query, modify, and manage SQLite, SQL Server, PostgreSQL, and MySQL data sources through a consistent set of tools.
How to use
Use the MCP server by configuring Claude Desktop to launch the MCP process for each database type you intend to work with. You interact with the server through Claude by issuing supported tools such as reading data, writing data, and managing schemas. The server handles the actual database connections and returns results to Claude for you to use in prompts and workflows.
How to install
Prerequisites you need before installation: Node.js 18 or later. Ensure you have access to a command line and appropriate permissions to install global npm packages if you plan to use the direct usage path.
Step-by-step installation and setup you can follow to get started:
# Prerequisite: ensure Node.js is installed (v18+)
node -v
npm -v
# Install the MCP server package globally for direct usage
npm install -g @executeautomation/database-server
# If you prefer to run from source locally, clone the repository and install locally
# git clone https://github.com/executeautomation/database-server.git
# cd database-server
# npm install
# npm run build
Configuration and usage notes
Configure Claude Desktop to launch the MCP server for each database type you will use. The following examples show how to wire up four MCP configurations directly in Claude Desktop:
{
"mcpServers": {
"sqlite": {
"command": "npx",
"args": [
"-y",
"@executeautomation/database-server",
"/path/to/your/database.db"
]
},
"sqlserver": {
"command": "npx",
"args": [
"-y",
"@executeautomation/database-server",
"--sqlserver",
"--server", "your-server-name",
"--database", "your-database-name",
"--user", "your-username",
"--password", "your-password"
]
},
"postgresql": {
"command": "npx",
"args": [
"-y",
"@executeautomation/database-server",
"--postgresql",
"--host", "your-host-name",
"--database", "your-database-name",
"--user", "your-username",
"--password", "your-password"
]
},
"mysql": {
"command": "npx",
"args": [
"-y",
"@executeautomation/database-server",
"--mysql",
"--host", "your-host-name",
"--database", "your-database-name",
"--port", "3306",
"--user", "your-username",
"--password", "your-password"
]
}
}
}
Local development configuration
If you are developing locally, configure Claude Desktop to use the locally built MCP server binary and pass the appropriate database connection details.
{
"mcpServers": {
"sqlite": {
"command": "node",
"args": [
"/absolute/path/to/mcp-database-server/dist/src/index.js",
"/path/to/your/database.db"
]
},
"sqlserver": {
"command": "node",
"args": [
"/absolute/path/to/mcp-database-server/dist/src/index.js",
"--sqlserver",
"--server", "your-server-name",
"--database", "your-database-name",
"--user", "your-username",
"--password", "your-password"
]
},
"postgresql": {
"command": "node",
"args": [
"/absolute/path/to/mcp-database-server/dist/src/index.js",
"--postgresql",
"--host", "your-host-name",
"--database", "your-database-name",
"--user", "your-username",
"--password", "your-password"
]
},
"mysql": {
"command": "node",
"args": [
"/absolute/path/to/mcp-database-server/dist/src/index.js",
"--mysql",
"--host", "your-host-name",
"--database", "your-database-name",
"--port", "3306",
"--user", "your-username",
"--password", "your-password"
]
}
}
}
Available database tools and capabilities
The MCP server exposes a set of tools you can invoke from Claude to interact with databases. These include reading data, writing data, managing schemas, and exporting results.
Development and maintenance
To develop or extend the MCP server locally, you can run the development workflow if you are contributing code. Use the project’s build and development commands to iterate quickly.
Available tools
read_query
Execute SELECT queries to read data from the connected database.
write_query
Execute INSERT, UPDATE, or DELETE queries to modify data.
create_table
Create a new table in the database using a CREATE TABLE statement.
alter_table
Modify the schema of an existing table using ALTER TABLE.
drop_table
Remove a table from the database. Requires confirmation.
list_tables
Retrieve a list of all tables present in the connected database.
describe_table
View the schema information for a specific table.
export_query
Export query results as CSV or JSON for external use.
append_insight
Add a business insight to the memo for later reference.
list_insights
List all stored business insights.