AtlaCP
An MCP interface for Atlassian products, including Jira and Bitbucket.
atlacp
An MCP (Model Context Protocol) interface for Bitbucket.
Features
Supported tools
bitbucket_add_pr_comment- add a comment to a pull requestbitbucket_approve_pr- approve a pull requestbitbucket_create_pr- create a pull requestbitbucket_create_pr_task- create a task on a pull requestbitbucket_get_file_content- get the content of a file in a pull requestbitbucket_get_pr_diff- get the diff of a pull requestbitbucket_get_pr_diffstat- get the diffstat of a pull requestbitbucket_list_pr_tasks- list tasks on a pull requestbitbucket_merge_pr- merge a pull requestbitbucket_read_pr- read a pull requestbitbucket_request_pr_changes- request changes on a pull requestbitbucket_update_pr- update a pull requestbitbucket_update_pr_task- update a task on a pull request
Supported transports
- Streamable HTTP (default)
- SSE
- STDIO
Quick Start
See detailed version here
Configure accounts
The tool is designed to be running locally on developer's machine. In order to run the tool you need to configure your Atlassian accounts first. For bitbucket you need to create a personal access token that can read and write to the repository.
Example atlassian-accounts.json file:
{
"accounts": [
{
"name": "user",
"default": true,
"bitbucket": { "type": "Basic", "value": "ATBBxxxxxxxxxxxxxxxx" }
}
]
}
You may optionally configure multiple accounts for different roles or different workspaces, for example you may have user and bot accounts. See quick-start/atlassian-accounts-stub.json for more details.
More on Atlassian tokens:
- Personal API Tokens (keep in mind to create a basic token for API use). When using personal access tokens, all requests will be made on behalf of the user.
- Bitbucket Access Tokens - good for bots and other automation tools.
Start the MCP server
Start docker container pointing on the atlassian-accounts.json file:
docker run -d --name atlacp-mcp \
--restart=always \
-p 8080:8080 \
-v $(pwd)/atlassian-accounts.json:/app/atlassian-accounts.json \
ghcr.io/gemyago/atlacp-mcp:latest \
-a /app/atlassian-accounts.json \
http
Integrate AI tools
Cursor MCP config (.cursor/mcp.json) section may look like this:
{
"mcpServers": {
"Atlassian MCP": {
"url": "http://localhost:8080"
}
}
}
Once configured, try to send a prompt to the editor, similar to below:
Check pull request 12345 from bitbucket repo owner/repo-name
You should see a response with PR details.
Pick appropriate transport
Root url will serve Streamable HTTP transport. You can use SSE transport by appending /sse to the root url. Example:
http://localhost:8080- Streamable HTTP transporthttp://localhost:8080/sse- SSE transport
STDIO is supported as well. Use docker run with stdio subcommand instead of http to use it.
License
MIT
Related Servers
early-mcp
Complete MCP server for Early (Timeular) time tracking - 46 tools for tracking, entries, activities, folders, tags, reports. Created with Claude
CodeRide
Task management redesigned for AI, integrated via the CodeRide MCP server.
AI MUSIC MCP
The World's First AI Music MCP Beyond images and video, your agent can now generate music.
AutoCAD MCP Server
Integrates AutoCAD with large language models (LLMs) for natural language interaction. Requires AutoCAD 2018+ on Windows.
ClickUp MCP Server (Enhanced Fork)
An MCP server for integrating ClickUp tasks with AI applications, featuring task dependency management and bug fixes.
GranolaMCP
An MCP server for accessing and analyzing Granola.ai meeting data.
Laravel Boost
Laravel Boost is an MCP server equipped with over 15 specialized tools designed to streamline AI-assisted coding workflows.
EmoVideoAna
analytics emotion of video
TaskFlow
An MCP server for integrating task management capabilities into Claude Desktop.
Breathe HR
Provides secure, read-write access to Breathe HR data for AI assistants.