home / mcp / bitbucket mcp server

Bitbucket MCP Server

This read-only MCP Server allows you to connect to Bitbucket data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Bitbucket (https://www.cdata.com/drivers/bitbucket/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-bitbucket-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/bitbucket.prp"
      ]
    }
  }
}

You can query live Bitbucket data through a dedicated MCP server that exposes data via MCP tools, enabling large language models to read from Bitbucket without writing SQL. This read-only MCP server wraps the CData JDBC Driver to present Bitbucket data as relational models, making it easy to ask natural language questions and get up-to-date results.

How to use

Once you have the MCP server running, you interact with it using an MCP-compatible client. You don’t need to write SQL. Instead, you issue requests that leverage the built‑in MCP tools to discover available data and run read-only queries. Typical use cases include asking questions like which accounts have certain activity, retrieving lists of tables and columns to understand the data model, and performing read-only queries across Bitbucket data.

How to install

Prerequisites you need before installation:

Install Java Runtime Environment (JRE) 8+ so you can run the MCP server JAR.

Install a Java build tool if you plan to build the MCP server from source (optional if you use a prebuilt JAR): Maven.

Step-by-step commands

# 1. Build the MCP server (if you are starting from source)
# mvn clean install
# This produces the JAR: CDataMCP-jar-with-dependencies.jar

# 2. Prepare the Bitbucket MCP configuration (bitbucket.prp) with your JDBC connection details
# Include Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, Tables as shown in the source setup

# 3. Run the MCP server on its own (stdio mode)
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/bitbucket.prp

MCP server configuration example

{
  "mcpServers": {
    "bitbucket_mcp": {
      "type": "stdio",
      "command": "java",
      "args": ["-jar", "/PATH/TO/CDataMCP-jar-with-dependencies.jar", "/PATH/TO/bitbucket.prp"]
    }
  }
}

Available tools

bitbucket_get_tables

Retrieves a list of tables available in the data source. The output is returned in CSV format with column headers on the first line.

bitbucket_get_columns

Retrieves a list of columns for a specific table. The output is CSV with column headers on the first line.

bitbucket_run_query

Executes a SQL SELECT query against the Bitbucket data exposed by the MCP server.