Database Explorer MCP connects assistants to PostgreSQL, MySQL or Firestore for connection setup, schema inspection, queries and exports.
Database Explorer MCP connects assistants to PostgreSQL, MySQL or Firestore for connection setup, schema inspection, queries and exports.
The TypeScript server offers distinct connection tools for PostgreSQL, MySQL and Firestore. Once connected, an assistant can list tables, inspect triggers or functions, run a query and export a table's schema or data. The active database service belongs to the running server process, so choose the intended connection before issuing a query.
The repository documents a Node.js source installation and an npm build that produces dist/index.js. Register that compiled file as a stdio server. Package metadata defines a binary name, but this profile uses the documented source route rather than assuming that a registry installation is available.
PostgreSQL and MySQL take host, database, user and password values through their connection tools. Firestore takes a project ID and service-account key file path. These are different credential paths; a generic API key does not configure all three. Keep credentials in the intended client and review the tool trace when testing a connection.
The query tool executes a supplied database query. Its permissions therefore come from the database account, rather than from a promise that the MCP server is read-only. For a schema review, start with a read-only account and a known table. Compare column definitions and a small result set with the database console before relying on an exported schema.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| !pg | Connect to PostgreSQL using supplied connection fields. |
| !mysql | Connect to MySQL using supplied connection fields. |
| !firestore | Connect to Firestore using a project ID and key file. |
| !tables | List available tables or collections. |
| !triggers | Inspect database triggers. |
| !functions | Inspect database functions. |
| !query | Execute a query using the active database connection. |
| !export-db | Export the schema of a specified table. |
| !export-data | Export data from a specified table. |
{
"mcpServers": {
"database-explorer": {
"command": "node",
"args": [
"/ABSOLUTE_PATH/db-mcp-tool/dist/index.js"
]
}
}
}Install dependencies and run npm run build in the repository. Replace the absolute path; connection credentials are supplied to the corresponding tools.
Node.js, the built source project and credentials for the selected database.
Inspect PostgreSQL schemas and run read-only queries with the archived MCP reference server. Review its maintenance status before choosing it.
Connect the Notion MCP server to search workspace content and work with pages and databases through Notion’s hosted OAuth service.
GLP-1 provider directory, peptide database, and medication comparison tools.
CData JDBC Driver connects to Google Spanner by exposing them as relational SQL models.
A Model Context Protocol (MCP) server for managing and querying knowledge bases through vector databases, built on top of the dynamic-mcp-server (DMS) framework.
SQL to PySpark conversion, AWS Glue job generation, and Spark code optimization.