Skip to main content
Glama
amansingh63

DBHub Analytics

by amansingh63
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

npm version License: MIT

Built on top of DBHub by Bytebase.

What is DBHub Analytics?

DBHub Analytics is an open-source MCP (Model Context Protocol) server that connects AI assistants like Claude Desktop, Claude Code, Cursor, VS Code Copilot, and other MCP-compatible clients to your databases. Query Databricks SQL warehouses, Google BigQuery datasets, PostgreSQL, MySQL, and more — all through a single unified interface.

            +------------------+    +--------------+    +------------------+
            |                  |    |              |    |                  |
            |  Claude Desktop  +--->+              +--->+    PostgreSQL    |
            |                  |    |              |    |                  |
            |  Claude Code     +--->+              +--->+    SQL Server    |
            |                  |    |    DBHub     |    |                  |
            |  Cursor          +--->+   Analytics  +--->+    SQLite        |
            |                  |    |              |    |                  |
            |  VS Code         +--->+              +--->+    MySQL         |
            |                  |    |              |    |                  |
            |  Copilot CLI     +--->+              +--->+    MariaDB       |
            |                  |    |              |    |                  |
            |                  |    |              +--->+    Databricks    |
            |                  |    |              |    |                  |
            |                  |    |              +--->+    BigQuery      |
            |                  |    |              |    |                  |
            +------------------+    +--------------+    +------------------+
                 MCP Clients           MCP Server             Databases

Related MCP server: mcp-ohmy-sql

Key Features

  • Cloud Data Warehouses: Connect to Databricks SQL and Google BigQuery for analytics workloads

  • Traditional Databases: Full support for PostgreSQL, MySQL, MariaDB, SQL Server, SQLite

  • Multi-Database: Connect to multiple databases simultaneously with a single TOML config file

  • Schema Explorer: Progressive disclosure — browse catalogs, datasets, schemas, tables, and columns

  • Safety Guardrails: Read-only mode, row limits, and query timeouts to prevent runaway operations

  • Secure Access: SSH tunneling, SSL/TLS encryption, and service account authentication

  • Zero Config: Just provide a DSN — no drivers to install, no complex setup

Supported Databases

Database

DSN Protocol

Status

PostgreSQL

postgres://

Stable

MySQL

mysql://

Stable

MariaDB

mariadb://

Stable

SQL Server

sqlserver://

Stable

SQLite

sqlite:///

Stable

Databricks SQL

databricks://

Stable

Google BigQuery

bigquery://

Stable

MCP Tools

Tool

Description

execute_sql

Execute SQL queries with read-only enforcement and row limiting

search_objects

Browse catalogs, schemas, tables, columns, indexes, and routines

Custom Tools

Define reusable, parameterized SQL queries in dbhub.toml

Quick Start

NPM (recommended)

npx dbhub-analytics --dsn "postgres://user:password@localhost:5432/dbname"

Databricks SQL

npx dbhub-analytics --dsn "databricks://token:YOUR_TOKEN@your-workspace.cloud.databricks.com/sql/2.0/warehouses/your_warehouse_id"

Google BigQuery

npx dbhub-analytics --dsn "bigquery://your-gcp-project/your_dataset?keyFile=/path/to/service-account.json&location=US"

Docker

docker run --rm --init \
   --name dbhub-analytics \
   --publish 8080:8080 \
   amansingh63/dbhub-analytics \
   --transport http \
   --port 8080 \
   --dsn "postgres://user:password@localhost:5432/dbname"

Demo Mode

npx dbhub-analytics --demo

Connect to Your AI Assistant

Claude Desktop / Claude Code

Add to your claude_desktop_config.json or .mcp.json:

{
  "mcpServers": {
    "dbhub-analytics": {
      "command": "npx",
      "args": ["-y", "dbhub-analytics", "--dsn", "bigquery://your-project/your_dataset?keyFile=/path/to/sa.json&location=US"]
    }
  }
}

GitHub Copilot (VS Code)

Add to your .vscode/mcp.json:

{
  "servers": {
    "dbhub-analytics": {
      "command": "npx",
      "args": ["-y", "dbhub-analytics", "--dsn", "postgres://user:pass@localhost:5432/dbname"]
    }
  }
}

Cursor

Add to your Cursor MCP settings (~/.cursor/mcp.json):

{
  "mcpServers": {
    "dbhub-analytics": {
      "command": "npx",
      "args": ["-y", "dbhub-analytics", "--dsn", "databricks://token:YOUR_TOKEN@host/sql/2.0/warehouses/ID"]
    }
  }
}

Windsurf

Add to your Windsurf MCP config (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "dbhub-analytics": {
      "command": "npx",
      "args": ["-y", "dbhub-analytics", "--dsn", "mysql://user:pass@localhost:3306/dbname"]
    }
  }
}

Multi-Database via TOML Config

For connecting to multiple databases, use a TOML config file with any of the above clients:

{
  "mcpServers": {
    "dbhub-analytics": {
      "command": "npx",
      "args": ["-y", "dbhub-analytics", "--config", "/path/to/dbhub.toml"]
    }
  }
}

Configuration

DSN Connection Strings

Database

Format

PostgreSQL

postgres://user:pass@host:5432/dbname?sslmode=require

MySQL

mysql://user:pass@host:3306/dbname

MariaDB

mariadb://user:pass@host:3306/dbname

SQL Server

sqlserver://user:pass@host:1433/dbname

SQLite

sqlite:///path/to/file.db or sqlite:///:memory:

Databricks

databricks://token:TOKEN@host/sql/2.0/warehouses/ID?catalog=CAT&schema=SCH

BigQuery

bigquery://PROJECT_ID/DATASET?keyFile=/path/to/key.json&location=US

Multi-Database Setup (TOML)

Connect to multiple databases simultaneously. Create a dbhub.toml file:

[[sources]]
id = "databricks_prod"
type = "databricks"
host = "adb-xxx.azuredatabricks.net"
password = "dapi..."
path = "/sql/2.0/warehouses/abc123"

[[sources]]
id = "bigquery_analytics"
type = "bigquery"
project = "my-gcp-project"
database = "analytics_dataset"
location = "US"

[[sources]]
id = "postgres_prod"
type = "postgres"
host = "localhost"
port = 5432
database = "production"
user = "dbuser"
password = "secret"

Then run:

npx dbhub-analytics --config dbhub.toml

See Multi-Database Configuration and Command-Line Options for complete documentation.

Use Cases

  • Data Analysts: Ask Claude to query your Databricks or BigQuery data warehouse in natural language

  • Backend Engineers: Explore database schemas, run diagnostic queries, and debug issues via AI

  • DevOps/SRE: Connect to production read-replicas safely with read-only mode and row limits

  • Data Scientists: Query multiple databases simultaneously — join insights across PostgreSQL and BigQuery

Development

# Install dependencies
pnpm install

# Run in development mode
pnpm dev

# Build for production
pnpm build

# Run tests
pnpm test

Credits

Built on top of DBHub by Bytebase, an open-source database DevSecOps platform. Licensed under MIT.

This server cannot be installed

A
license - permissive license
-
quality - not tested
D
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • DBHub

    OrionPotter
    A
    license
    -
    quality
    -
    maintenance
    A universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
    Last updated
    18

  • mcp-ohmy-sql

    MacHu-GWU
    -
    license
    -
    quality
    C
    maintenance
    An MCP server that bridges AI assistants with SQL databases, enabling natural language querying across multiple database types with built-in optimization and security.
    Last updated
    3

  • Legion Database MCP Server

    fastmcp-me
    A
    license
    -
    quality
    D
    maintenance
    A unified MCP server for querying and managing multiple database types (PostgreSQL, MySQL, SQL Server, etc.) via natural language through AI assistants.
    Last updated
    GPL 3.0

  • mcp-data-source

    Crankhead
    F
    license
    -
    quality
    C
    maintenance
    Multi-datasource MCP server that connects AI assistants to 6 database types (MySQL, PostgreSQL, ClickHouse, MongoDB, SQLite, Huawei DWS) with dynamic configuration, encrypted credential storage, and schema discovery.
    Last updated

View all related MCP servers

Related MCP Connectors

  • mcp

    GibsonAI MCP server: manage your databases with natural language

  • anythingmcp

    Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.

  • nlqdb — analytical memory for AI agents

    Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/amansingh63/dbhub-analytics'

If you have feedback or need assistance with the MCP directory API, please join our Discord server