# DBHub Analytics [Health: Active]

**Category:** 🗄️ Databases  
**Repository:** https://github.com/amansingh63/dbhub-analytics  
**GitHub Stars:** 0  
**npm Downloads (last month):** 204  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/dbhub-analytics

## Description
MCP server for Databricks, BigQuery, PostgreSQL, MySQL, SQL Server, SQLite, MariaDB

## Tools
Capabilities this server exposes over MCP:

- **execute_sql** — Execute SQL queries with read-only enforcement and row limiting
- **search_objects** — Browse catalogs, schemas, tables, columns, indexes, and routines

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "dbhub-analytics": {
    "command": "npx",
    "args": ["-y","dbhub-analytics"]
  }
}
```

## Documentation

## What DBHub Analytics MCP server does

DBHub Analytics MCP server provides a single MCP interface for querying and inspecting several database systems. Supported connections include PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, Databricks SQL warehouses, and Google BigQuery datasets. An MCP-compatible assistant can use the server to send SQL statements, inspect database structure, and work with metadata without requiring a separate MCP server for each database type.

The project is built on DBHub and is intended for analytical and operational database access through AI clients. It can be used with local databases, cloud warehouses, or multiple sources configured together. The available interface is deliberately focused: SQL execution and object discovery are the core operations.

## How it works

The server starts with either a database connection string or a TOML configuration file. A DSN identifies the database type and connection details, such as the host, port, database, warehouse, project, dataset, or authentication parameters. For multiple sources, a TOML file defines each source with its own identifier and connection settings.

Clients communicate with the process through MCP. Client configuration examples are provided for Claude Desktop, Claude Code, Cursor, VS Code Copilot, and Windsurf.

SQL access includes read-only enforcement and row limiting. The project also describes query timeouts, SSH tunneling, SSL/TLS encryption, and service-account authentication as supported configuration or access features. These controls make the server suitable for querying read replicas or analytical systems where unrestricted writes and unbounded result sets should be avoided.

## Setup and configuration

The simplest setup passes a DSN to the npm package:

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

Use a database-specific DSN for Databricks or BigQuery. BigQuery connections can specify a GCP project, dataset, service-account key file, and location. SQLite accepts a file path or an in-memory database.

For several databases, create `dbhub.toml` with a `[[sources]]` entry for each connection, then start the server with `--config`. This lets one MCP configuration expose Databricks, BigQuery, PostgreSQL, or other supported sources together. A demo mode is also available through `npx dbhub-analytics --demo`.

## Tools and capabilities

DBHub Analytics MCP server exposes these MCP tools:

- `execute_sql`: Runs SQL with read-only enforcement and row limiting.
- `search_objects`: Searches or browses catalogs, schemas, tables, columns, indexes, and routines.

The configuration can also define reusable, parameterized SQL queries as custom tools in `dbhub.toml`. This is useful when an application needs a known query shape rather than unrestricted ad hoc SQL. Schema discovery follows a progressive path from broader objects such as catalogs or datasets toward tables and columns.

## Limitations and notes

Read-only behavior is a stated safeguard, so this server should not be selected when an agent must insert, update, delete, or administer database resources.

Authentication and network access remain dependent on the target database and its connection settings. Examples include credentials in DSNs, BigQuery service-account files, SSL/TLS options, and SSH tunneling. Protect configuration files and connection strings because they may contain sensitive access information.

The README names stable support for seven database protocols but does not describe feature parity for every database engine. SQL syntax, metadata availability, authentication behavior, and warehouse-specific options may therefore vary by source. The DBHub Analytics MCP server is best evaluated against the particular database and client configuration you plan to use.

_Full upstream README: https://allmcps.com/mcp/dbhub-analytics/readme_