db-mcp-tool
The Database Explorer MCP Tool enables exploration and management of PostgreSQL, MySQL, and Firestore databases via a command-line interface integrated with Cursor.
Key capabilities:
Connect to databases: PostgreSQL (
!pg), MySQL (!mysql), and Firestore (!firestore)Database operations:
List tables (
!tables)View triggers (
!triggers)List functions (
!functions)Execute SQL queries (
!query) - PostgreSQL and MySQL onlyExport table schemas (
!export-db)Export table data as INSERT statements (
!export-data)
Error handling for connection failures, query execution errors and export issues
Integration with Cursor through building and configuring the tool
Allows connecting to and interacting with Google Firestore databases, including basic database operations (though limited due to Firestore's NoSQL nature).
Allows connecting to and interacting with MySQL databases, including listing tables, viewing triggers, listing functions, executing SQL queries, and exporting schema and data.
Allows connecting to and interacting with PostgreSQL databases, including listing tables, viewing triggers, listing functions, executing SQL queries, and exporting schema and data.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@db-mcp-tool show me all tables in the connected PostgreSQL database"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Database Explorer MCP Tool
A powerful Model Context Protocol (MCP) tool for exploring and managing different types of databases including PostgreSQL, MySQL, and Firestore.
Features
Multiple Database Support
PostgreSQL
MySQL
Firestore
Database Operations
Connect to databases
List tables
View triggers
List functions
Execute SQL queries (PostgreSQL and MySQL)
Export table schemas
Export table data
Related MCP server: Database MCP Server
Integration with Cursor
Before adding the tool to Cursor, you need to build the project:
Clone the repository
Install dependencies:
npm installBuild the project:
npm run build
To add the tool to Cursor:
Open Cursor settings
Navigate to "Model Context Protocol (MCP)" section
Click "Add New Tool"
Fill in the following details:
{ "name": "database-explorer", "command": "node /path/to/project/dist/index.js", "description": "Database Explorer MCP Tool" }Note: Replace
/path/to/projectwith the actual path to your project directory.Save the settings
Restart Cursor
Using the Tool:
After setup, you can connect to your database using one of these commands:
For PostgreSQL: Use
!pgwith connection detailsFor MySQL: Use
!mysqlwith connection detailsFor Firestore: Use
!firestorewith connection details
Once connected, you can use various database operations:
!tablesto list all tables!triggersto view triggers!functionsto list functions!queryto execute SQL queries!export-dbto export table schemas!export-datato export table data
See the Commands section below for detailed usage examples.
Commands
Connection Commands
!pg- Connect to PostgreSQL database{ "connection": { "host": "hostname", "port": 5432, "database": "dbname", "user": "username", "password": "password" } }!mysql- Connect to MySQL database{ "connection": { "host": "hostname", "port": 3306, "database": "dbname", "user": "username", "password": "password" } }!firestore- Connect to Firestore database{ "connection": { "projectId": "your-project-id", "keyFilename": "path/to/keyfile.json" } }
Database Operation Commands
!tables- List all tables in the connected database!triggers- List all triggers in the connected database!functions- List all functions in the connected database!query- Execute SQL query (PostgreSQL and MySQL only){ "query": "SELECT * FROM table_name" }!export-db- Export table schema{ "table": "table_name" }!export-data- Export table data as INSERT statements{ "table": "table_name" }
Requirements
Node.js
Required database drivers:
pgfor PostgreSQLmysql2for MySQL@google-cloud/firestorefor Firestore
Usage
Make sure you have the necessary database credentials
Connect to your database using the appropriate connection command
Use the available commands to explore and manage your database
Error Handling
The tool includes comprehensive error handling for:
Connection failures
Query execution errors
Schema and data export issues
Invalid database operations
Notes
Firestore support is limited to basic operations due to its NoSQL nature
SQL operations are only available for PostgreSQL and MySQL
Available Tools
9 tools!export-dataD
Inputs: table (required).
!export-dbD
Inputs: table (required).
!firestoreD
Inputs: connection (required).
!functionsD
Inputs: no named parameters.
!mysqlD
Inputs: connection (required).
!pgD
Inputs: connection (required).
!queryD
Inputs: query (required).
!tablesD
Inputs: no named parameters.
!triggersD
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
The tools are completely indistinguishable due to the lack of descriptions and ambiguous naming. For example, '!export-data' and '!export-db' likely overlap significantly, while '!mysql' and '!pg' might both handle database operations without clear differentiation. Without descriptions, an agent cannot determine the purpose or boundaries of any tool.
The naming is inconsistent with a mix of conventions: some tools use hyphens (e.g., '!export-data'), others are single words (e.g., '!mysql'), and some are abbreviations (e.g., '!pg'). While all start with '!', there is no predictable verb_noun pattern or consistent style, making it hard to infer relationships.
With 9 tools, the count is reasonable for a database-related server, but the lack of descriptions makes it impossible to assess if this number is well-scoped. It could be appropriate if each tool covers a distinct aspect, but currently, it feels borderline due to the ambiguity.
The server appears to target database operations, but without descriptions, it is impossible to assess coverage. Tools like '!query' and '!tables' suggest basic operations, but there are likely significant gaps (e.g., no clear create, update, or delete tools) and no way to determine if the surface supports a complete workflow.
Maintenance
Related MCP Connectors
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Managed Postgres MCP: projects, SQL, docs search, and storage buckets via OAuth.
Hosted PostgreSQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
The AI that understands raw data: Schema over your tables and databases, as MCP tools.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables powerful PostgreSQL database management capabilities including analysis, schema management, data migration, and monitoring through natural language interactions.1810,856 npm204AGPL 3.0
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides tools for connecting to and interacting with various database systems (SQLite, PostgreSQL, MySQL/MariaDB, SQL Server) through a unified interface.3-
- -licenseNot gradedqualityNot gradedmaintenanceA Model Context Protocol server that provides tools for interacting with databases, including PostgreSQL, DuckDB, and Google Cloud Storage Parquet files.2-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server for interacting with MSSQL and PostgreSQL databases, offering tools for schema exploration and SQL execution. It features configurable query modes for safety and supports advanced authentication methods like Windows Auth and SSL.11 npmMIT