Atlassian Bitbucket MCP
Enables interaction with Bitbucket through the Model Context Protocol, allowing users to manage pull requests, add comments, review code, create tasks, and perform other repository operations using natural language.
README
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 accounts-config.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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.