Dbeaver Jdbc

joutvhu1stars

A high-performance, universal Model Context Protocol server built with the official Model Context Protocol Java SDK that connects AI assistants directly to all database connections configured in DBeav

Databases

Install Run on PlugMCP

GitHub

Run on PlugMCP

1# Dbeaver Jdbc

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: Apache-2.0
Last checked: 2026-10-28

Stars: 1
Tools: —
Uptime: —

Overview

About Dbeaver Jdbc

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Dbeaver Jdbc?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Dbeaver Jdbc need an API key?

No required environment variable is listed on this record.

What transport does Dbeaver Jdbc use?

Dbeaver Jdbc runs locally over stdio.

When was Dbeaver Jdbc last checked?

Last checked 2026-10-28. A high-performance, universal Model Context Protocol server built with the official Model Context Protocol Java SDK that connects AI assistants directly to all database connections configured in DBeaver.

From the publisher

Documentation

DBeaver JDBC MCP Server

A high-performance, universal Model Context Protocol (MCP) server built with the official Model Context Protocol Java SDK (io.modelcontextprotocol.sdk:mcp) that connects AI assistants (Kiro, Claude Desktop, Cursor, etc.) directly to all database connections configured in DBeaver.

Unlike traditional MCP servers that require separate Python drivers, C++ build tools, or ODBC libraries for each database type, dbeaver-jdbc-mcp runs natively on Java and reuses the exact JDBC drivers already downloaded and managed by DBeaver.

🌟 Key Highlights

Official Java SDK: Powered by io.modelcontextprotocol.sdk:mcp-core (Version 2.0.1) and Project Reactor, compliant with MCP specification revisions 2024-11-05 and 2025-11-25.
100% Database Coverage: Supports any database that DBeaver can connect to (PostgreSQL, MySQL, SQL Server, Oracle, SQLite, Snowflake, ClickHouse, DuckDB, Trino, DB2, Informix, etc.).
Zero Driver Setup: Automatically scans and dynamically loads JDBC .jar drivers from %APPDATA%\DBeaverData\drivers\.
Zero Runtime Installation: Automatically detects and uses DBeaver's bundled OpenJDK JRE — no need to install Python, Node.js, C++ compilers, or a separate Java runtime.
Cross-Platform: Seamlessly works on Windows, macOS, and Linux.

🚀 Easy Ways to Install & Run

You can choose any of the 3 standard options below to configure dbeaver-jdbc-mcp in your AI client (e.g. mcp.json in Kiro, Claude Desktop, or Cursor):

Option 1: Run directly via `npx` (Recommended - Zero Installation)

No manual download required. Just add to your mcp.json:

{
  "mcpServers": {
    "dbeaver": {
      "command": "npx",
      "args": ["-y", "dbeaver-jdbc-mcp"]
    }
  }
}

Option 2: Run via `jbang` (Maven Central)

If you have jbang installed:

{
  "mcpServers": {
    "dbeaver": {
      "command": "jbang",
      "args": ["run", "com.github.joutvhu:dbeaver-jdbc-mcp:1.0.0"]
    }
  }
}

Option 3: Download Portable ZIP from GitHub Releases

Download dbeaver-jdbc-mcp-x.x.x-portable.zip from the GitHub Releases page.
Extract it anywhere on your machine.
Configure your mcp.json:

On Windows:

{
  "mcpServers": {
    "dbeaver": {
      "command": "C:\\path\\to\\dbeaver-jdbc-mcp\\dbeaver-jdbc-mcp.cmd"
    }
  }
}

On macOS / Linux:

{
  "mcpServers": {
    "dbeaver": {
      "command": "/path/to/dbeaver-jdbc-mcp/dbeaver-jdbc-mcp.sh"
    }
  }
}

(The .cmd and .sh scripts automatically detect DBeaver's installation path via Windows Registry, AppData, macOS /Applications, or Linux /usr/share/dbeaver).

🛠 Build from Source

Requirements: JDK 17+ (No need to install Maven, as the Maven Wrapper is included):

On Windows:

.\mvnw.cmd clean package

On macOS / Linux:

./mvnw clean package

This generates the standalone Fat JAR at dbeaver-jdbc-mcp.jar (and in target/dbeaver-jdbc-mcp.jar).

🧪 Publish & Test Locally (Install to `npm -g`)

To test the package locally as a real global CLI tool:

npm run publish:local

Script automatically builds the Fat JAR, packages it, and installs it directly into npm -g. You can then run dbeaver-jdbc-mcp from anywhere or configure "command": "dbeaver-jdbc-mcp" in your mcp.json. (To uninstall: npm uninstall -g dbeaver-jdbc-mcp).

🛠 Available Tools

Tool	Description	Parameters
`list_connections`	List all DBeaver database connections (passwords safely redacted).	`details` (boolean, optional)
`test_connection`	Test connectivity, measuring latency and server version.	`connection_id` (string, required)
`list_tables`	List tables and views across schemas using standard JDBC metadata.	`connection_id` (string), `schema` (optional), `include_views` (optional)
`describe_table`	Describe table columns (types, sizes, nullability, defaults, primary keys).	`connection_id` (string), `table_name` (string)
`query`	Execute a safe, read-only SQL query (`SELECT`, `EXPLAIN`, `SHOW`, `DESCRIBE`).	`connection_id` (string), `sql` (string), `max_rows` (optional, default 1000)
`export_query`	Execute a read-only query and export results as `json` or `csv`.	`connection_id` (string), `sql` (string), `format` ("json" \| "csv"), `max_rows` (optional)
`execute`	Execute safe data modification (`INSERT`, `UPDATE with WHERE`, `DELETE with WHERE`, `MERGE`). Blocked when `READ_ONLY=true`.	`connection_id` (string), `sql` (string)
`db_stats`	Retrieve database statistics (table count, server version, ping).	`connection_id` (string)
`debug_info`	Inspect DBeaver workspace path, detected driver JARs, and runtime status.	None

🔒 Safety & Security Rules

Read-Only by default: Write operations (execute tool) are disabled unless READ_ONLY=false is explicitly set in your environment.
Bulk Modification Prevention: UPDATE and DELETE statements must include a WHERE clause.
DDL & Admin Protection: DROP, TRUNCATE, ALTER, GRANT, REVOKE, CREATE USER, and SHUTDOWN are strictly blocked.
Credential Protection: Passwords and secrets are never returned in list_connections responses.

⚙️ Environment Variables

All settings can be customized using environment variables:

Variable	Description	Default
`READ_ONLY`	Block data modifications (`true`/`false`). When `true`, `execute` is disabled.	`true`
`DBEAVER_AES_KEY`	AES encryption key for decrypting `credentials-config.json` (hex string or text).	`babb4a9f774ab853c96c2d653dfe544a`
`DBEAVER_AES_IV`	AES Initialization Vector for credentials decryption (hex string or text).	16 zero bytes (`0x00...`)
`DBEAVER_WORKSPACE`	Custom path to DBeaver workspace directory.	Auto-detected (`%APPDATA%\DBeaverData\workspace6`)
`DBEAVER_DRIVERS_PATH`	Path to additional directory containing JDBC `.jar` drivers.	Auto-detected (`%APPDATA%\DBeaverData\drivers`)
`DBEAVER_QUERY_TIMEOUT_SECONDS`	Query execution timeout in seconds.	`0` (no timeout)
`DBEAVER_MAX_ROWS_LIMIT`	Hard ceiling for maximum rows returned per query.	`10000`
`DBEAVER_DEBUG`	Enable verbose diagnostic logging to stderr (`true`/`false`).	`false`

📦 Automated Release Pipeline

This project includes a continuous delivery pipeline in .github/workflows/release.yml. Whenever you create and publish a new Release on GitHub (e.g. tagging v1.0.0 and clicking Publish release):

Runs tests and builds the official Fat JAR.
Automatically uploads dbeaver-jdbc-mcp.jar, portable zip, .cmd, and .sh assets to that GitHub Release.
Automatically publishes the package to the NPM Registry (npx dbeaver-jdbc-mcp).
Signs and deploys artifacts to Maven Central (when Sonatype / GPG secrets are configured).

📄 License

This project is open-sourced under the Apache-2.0 License.

Dbeaver Jdbc

joutvhu1stars

Databases

Install Run on PlugMCP

GitHub

Run on PlugMCP

1# Dbeaver Jdbc

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: Apache-2.0
Last checked: 2026-10-28

Stars: 1
Tools: —
Uptime: —

Overview

About Dbeaver Jdbc

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Dbeaver Jdbc?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Dbeaver Jdbc need an API key?

No required environment variable is listed on this record.

What transport does Dbeaver Jdbc use?

Dbeaver Jdbc runs locally over stdio.

When was Dbeaver Jdbc last checked?

From the publisher

Documentation

DBeaver JDBC MCP Server

🌟 Key Highlights

Official Java SDK: Powered by io.modelcontextprotocol.sdk:mcp-core (Version 2.0.1) and Project Reactor, compliant with MCP specification revisions 2024-11-05 and 2025-11-25.
100% Database Coverage: Supports any database that DBeaver can connect to (PostgreSQL, MySQL, SQL Server, Oracle, SQLite, Snowflake, ClickHouse, DuckDB, Trino, DB2, Informix, etc.).
Zero Driver Setup: Automatically scans and dynamically loads JDBC .jar drivers from %APPDATA%\DBeaverData\drivers\.
Zero Runtime Installation: Automatically detects and uses DBeaver's bundled OpenJDK JRE — no need to install Python, Node.js, C++ compilers, or a separate Java runtime.
Cross-Platform: Seamlessly works on Windows, macOS, and Linux.

🚀 Easy Ways to Install & Run

You can choose any of the 3 standard options below to configure dbeaver-jdbc-mcp in your AI client (e.g. mcp.json in Kiro, Claude Desktop, or Cursor):

Option 1: Run directly via `npx` (Recommended - Zero Installation)

No manual download required. Just add to your mcp.json:

{
  "mcpServers": {
    "dbeaver": {
      "command": "npx",
      "args": ["-y", "dbeaver-jdbc-mcp"]
    }
  }
}

Option 2: Run via `jbang` (Maven Central)

If you have jbang installed:

{
  "mcpServers": {
    "dbeaver": {
      "command": "jbang",
      "args": ["run", "com.github.joutvhu:dbeaver-jdbc-mcp:1.0.0"]
    }
  }
}

Option 3: Download Portable ZIP from GitHub Releases

Download dbeaver-jdbc-mcp-x.x.x-portable.zip from the GitHub Releases page.
Extract it anywhere on your machine.
Configure your mcp.json:

On Windows:

{
  "mcpServers": {
    "dbeaver": {
      "command": "C:\\path\\to\\dbeaver-jdbc-mcp\\dbeaver-jdbc-mcp.cmd"
    }
  }
}

On macOS / Linux:

{
  "mcpServers": {
    "dbeaver": {
      "command": "/path/to/dbeaver-jdbc-mcp/dbeaver-jdbc-mcp.sh"
    }
  }
}

(The .cmd and .sh scripts automatically detect DBeaver's installation path via Windows Registry, AppData, macOS /Applications, or Linux /usr/share/dbeaver).

🛠 Build from Source

Requirements: JDK 17+ (No need to install Maven, as the Maven Wrapper is included):

On Windows:

.\mvnw.cmd clean package

On macOS / Linux:

./mvnw clean package

This generates the standalone Fat JAR at dbeaver-jdbc-mcp.jar (and in target/dbeaver-jdbc-mcp.jar).

🧪 Publish & Test Locally (Install to `npm -g`)

To test the package locally as a real global CLI tool:

npm run publish:local

🛠 Available Tools

Tool	Description	Parameters
`list_connections`	List all DBeaver database connections (passwords safely redacted).	`details` (boolean, optional)
`test_connection`	Test connectivity, measuring latency and server version.	`connection_id` (string, required)
`list_tables`	List tables and views across schemas using standard JDBC metadata.	`connection_id` (string), `schema` (optional), `include_views` (optional)
`describe_table`	Describe table columns (types, sizes, nullability, defaults, primary keys).	`connection_id` (string), `table_name` (string)
`query`	Execute a safe, read-only SQL query (`SELECT`, `EXPLAIN`, `SHOW`, `DESCRIBE`).	`connection_id` (string), `sql` (string), `max_rows` (optional, default 1000)
`export_query`	Execute a read-only query and export results as `json` or `csv`.	`connection_id` (string), `sql` (string), `format` ("json" \| "csv"), `max_rows` (optional)
`execute`	Execute safe data modification (`INSERT`, `UPDATE with WHERE`, `DELETE with WHERE`, `MERGE`). Blocked when `READ_ONLY=true`.	`connection_id` (string), `sql` (string)
`db_stats`	Retrieve database statistics (table count, server version, ping).	`connection_id` (string)
`debug_info`	Inspect DBeaver workspace path, detected driver JARs, and runtime status.	None

🔒 Safety & Security Rules

Read-Only by default: Write operations (execute tool) are disabled unless READ_ONLY=false is explicitly set in your environment.
Bulk Modification Prevention: UPDATE and DELETE statements must include a WHERE clause.
DDL & Admin Protection: DROP, TRUNCATE, ALTER, GRANT, REVOKE, CREATE USER, and SHUTDOWN are strictly blocked.
Credential Protection: Passwords and secrets are never returned in list_connections responses.

⚙️ Environment Variables

All settings can be customized using environment variables:

Variable	Description	Default
`READ_ONLY`	Block data modifications (`true`/`false`). When `true`, `execute` is disabled.	`true`
`DBEAVER_AES_KEY`	AES encryption key for decrypting `credentials-config.json` (hex string or text).	`babb4a9f774ab853c96c2d653dfe544a`
`DBEAVER_AES_IV`	AES Initialization Vector for credentials decryption (hex string or text).	16 zero bytes (`0x00...`)
`DBEAVER_WORKSPACE`	Custom path to DBeaver workspace directory.	Auto-detected (`%APPDATA%\DBeaverData\workspace6`)
`DBEAVER_DRIVERS_PATH`	Path to additional directory containing JDBC `.jar` drivers.	Auto-detected (`%APPDATA%\DBeaverData\drivers`)
`DBEAVER_QUERY_TIMEOUT_SECONDS`	Query execution timeout in seconds.	`0` (no timeout)
`DBEAVER_MAX_ROWS_LIMIT`	Hard ceiling for maximum rows returned per query.	`10000`
`DBEAVER_DEBUG`	Enable verbose diagnostic logging to stderr (`true`/`false`).	`false`

📦 Automated Release Pipeline

Runs tests and builds the official Fat JAR.
Automatically uploads dbeaver-jdbc-mcp.jar, portable zip, .cmd, and .sh assets to that GitHub Release.
Automatically publishes the package to the NPM Registry (npx dbeaver-jdbc-mcp).
Signs and deploys artifacts to Maven Central (when Sonatype / GPG secrets are configured).

📄 License

This project is open-sourced under the Apache-2.0 License.

Add this server

Host a copy with our keys and logs.

Server facts

About Dbeaver Jdbc

Tools

Questions

How do I install Dbeaver Jdbc?

Does Dbeaver Jdbc need an API key?

What transport does Dbeaver Jdbc use?

When was Dbeaver Jdbc last checked?

Documentation

DBeaver JDBC MCP Server

🌟 Key Highlights

🚀 Easy Ways to Install & Run

Option 1: Run directly via npx (Recommended - Zero Installation)

Option 2: Run via jbang (Maven Central)

Option 3: Download Portable ZIP from GitHub Releases

🛠 Build from Source

🧪 Publish & Test Locally (Install to npm -g)

🛠 Available Tools

🔒 Safety & Security Rules

⚙️ Environment Variables

📦 Automated Release Pipeline

📄 License

Add this server

Host a copy with our keys and logs.

Server facts

About Dbeaver Jdbc

Tools

Questions

How do I install Dbeaver Jdbc?

Does Dbeaver Jdbc need an API key?

What transport does Dbeaver Jdbc use?

When was Dbeaver Jdbc last checked?

Documentation

DBeaver JDBC MCP Server

🌟 Key Highlights

🚀 Easy Ways to Install & Run

Option 1: Run directly via npx (Recommended - Zero Installation)

Option 2: Run via jbang (Maven Central)

Option 3: Download Portable ZIP from GitHub Releases

🛠 Build from Source

🧪 Publish & Test Locally (Install to npm -g)

🛠 Available Tools

🔒 Safety & Security Rules

⚙️ Environment Variables

📦 Automated Release Pipeline

📄 License

Option 1: Run directly via `npx` (Recommended - Zero Installation)

Option 2: Run via `jbang` (Maven Central)

🧪 Publish & Test Locally (Install to `npm -g`)

Option 1: Run directly via `npx` (Recommended - Zero Installation)

Option 2: Run via `jbang` (Maven Central)

🧪 Publish & Test Locally (Install to `npm -g`)