Gives Claude direct access to PostgreSQL, MySQL, and SQLite databases through a secure query interface. Configure multiple connections via environment variables, mark any as read-only, and set timeouts to prevent runaway queries. Exposes tools for listing tables, inspecting schemas, running SELECT queries, and executing writes. All queries use prepared statements and block DDL operations like DROP or ALTER. Responses cap at 100 rows and 64KB by default. Useful when you want Claude to analyze production data, generate reports from live databases, or build features that query across multiple data sources without writing custom integration code.
MCP server for PostgreSQL, MySQL, and SQLite. Gives AI assistants secure database access via Model Context Protocol.
npx @pilat/mcp-datalink
Works with Claude Desktop, Claude Code, Cursor, Cline, and any MCP-compatible client.
Add to your MCP client config file (see config locations below):
{
"mcpServers": {
"datalink": {
"command": "npx",
"args": ["-y", "@pilat/mcp-datalink"],
"env": {
"DATALINK_ANALYTICS_URL": "postgresql://user:password@localhost:5432/analytics",
"DATALINK_ANALYTICS_READONLY": "true",
"DATALINK_INVENTORY_URL": "mysql://user:password@localhost:3306/inventory",
"DATALINK_CACHE_URL": "sqlite:///path/to/cache.db"
}
}
}
}
This creates three database connections: analytics (read-only), inventory, and cache.
| Variable | Description |
|---|---|
DATALINK_{NAME}_URL | Connection URL (creates database named {name}) |
DATALINK_{NAME}_READONLY | Set to true to block writes |
DATALINK_{NAME}_MAX_TIMEOUT | Max query timeout in ms (caps model requests) |
Connection URL formats:
# PostgreSQL
postgresql://user:password@localhost:5432/dbname
postgresql://user:password@localhost:5432/dbname?sslmode=require
# MySQL
mysql://user:password@localhost:3306/dbname
mysql://user:password@localhost:3306/dbname?ssl=true
# SQLite
sqlite:///path/to/database.db
sqlite:///Users/me/data/app.sqlite
sqlite://../relative/path/data.db
URLs support ${VAR} syntax to reference other environment variables:
{
"mcpServers": {
"datalink": {
"command": "npx",
"args": ["-y", "@pilat/mcp-datalink"],
"env": {
"DATALINK_MAIN_URL": "${DATABASE_URL}"
}
}
}
}
This allows reusing existing environment variables (like DATABASE_URL from your shell or .env file).
Supported syntax:
| Syntax | Description |
|---|---|
${VAR} | Expands to value of VAR, or keeps ${VAR} if unset |
${VAR:-default} | Expands to value of VAR, or default if unset |
Examples:
# Reference existing DATABASE_URL
DATALINK_MAIN_URL="${DATABASE_URL}"
# Build URL from parts
DATALINK_MAIN_URL="postgresql://${DB_USER}:${DB_PASS}@${DB_HOST}:5432/mydb"
# With default values
DATALINK_MAIN_URL="postgresql://localhost:${DB_PORT:-5432}/mydb"
| Client | Config file |
|---|---|
| Claude Code | ~/.claude.json (global) or .mcp.json (project) |
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Cursor | ~/.cursor/mcp.json or Settings → Features → MCP Servers |
| Cline | cline_mcp_settings.json or VS Code settings cline.mcpServers |
| Tool | Description |
|---|---|
list_databases | List configured database connections |
list_tables | List tables with row counts |
describe_table | Get schema, indexes, foreign keys |
query | Run SELECT queries |
execute | Run INSERT/UPDATE/DELETE |
explain | Show query execution plans |
DATALINK_MAX_TOTAL_SIZE)MAX_TIMEOUT caps itMIT
DATALINK_ANALYTICS_URL*secretDatabase connection URL. Pattern: DATALINK_<NAME>_URL where <NAME> identifies the database. Supports postgresql://, mysql://, or file path for SQLite.
DATALINK_ANALYTICS_READONLYSet to 'true' for read-only access. Pattern: DATALINK_<NAME>_READONLY
hovecapital/read-only-local-postgres-mcp-server
cocaxcode/database-mcp
io.github.infoinlet-marketplace/mcp-mysql
io.github.cybeleri/database-admin
io.github.yash-0620/postgres-mcp-secured