Install Bitbucket Data Center

Pick your client, copy the command, done.

claude mcp add -e "BITBUCKET_HOST=${BITBUCKET_HOST}" -e "BITBUCKET_API_TOKEN=${BITBUCKET_API_TOKEN}" bitbucket-dc -- uvx mcp-bitbucket-dc

Required:BITBUCKET_HOSTBITBUCKET_API_TOKEN

Environment Variables

Set these before running Bitbucket Data Center.

VariableDescriptionRequired

BITBUCKET_HOSTThe URL of your Bitbucket Data Center instance.Yes

BITBUCKET_API_TOKENPersonal access token with repository read/write permissions.Yes

Once configured, Bitbucket Data Center gives your AI agent access to:

bitbucket_code_searchSearch code across all repositories using Lucene syntax.

bitbucket_browseBrowse directory tree for files and folders at a specific path.

bitbucket_get_file_contentRetrieve raw file content with syntax highlighting.

bitbucket_list_filesRecursively list all file paths in a repository.

bitbucket_get_pull_requestsList pull requests filtered by state, direction, or text.

bitbucket_create_pull_requestCreate a new pull request.

bitbucket_post_pull_request_commentPost a general or inline comment on a pull request.

After setup, try these prompts with your AI agent:

→Search for CompanyInfoUpdater in the codebase.

→Show me the file structure of the api-service repo in PROJECT.

→Get the content of src/main/Application.java from repo backend.

→List open pull requests in PROJECT/my-repo.

→What branches exist in PROJECT/my-repo?

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed
BITBUCKET_HOST — The URL of your Bitbucket Data Center instance.
BITBUCKET_API_TOKEN — Personal access token with repository read/write permissions.

Save the docs, env vars, and workflow around Bitbucket Data Center in Conare so Claude Code, Codex, and Cursor remember it next time.