AtlaCP

by gemyago

Not rated
GitHub

About

An MCP interface for Atlassian products, including Jira and Bitbucket.

Details

Author
gemyago
Categories
Productivity, Project Management, Automation

Setup

Install AtlaCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/gemyago/atlacp

Follow the installation instructions in the repository README, then restart your MCP client.

Bitbucket tooling for developers and AI agents.

- bbmd- direct Bitbucket CLI for humans, scripts, and agent workflows.
- bbcp- MCP (Model Context Protocol) server for MCP-compatible editors and clients.

Thebbmdcli should be the superior to MCP when used by AI agents.

The installer placesbbmdandbbcpin~/.atlacp/binand updates your shell profile. Restart the shell, or source the updated profile before continuing. Followaccounts setupto configure Bitbucket account(s).

Usebbmd skillto teach your agent to use the cli. You can either write it to the agent relevant skill folder or add it somewhere in AGENTS.md.

### Bitbucket integration Run bbmd skill to learn how to work with bitbucket.

Or write the skill in either project-local scope or global scope:

# Opencode # Project-local mkdir -p .opencode/skills/bitbucket && bbmd skill > .opencode/skills/bitbucket/SKILL.md # Global mkdir -p ~/.opencode/skills/bitbucket && bbmd skill > ~/.opencode/skills/bitbucket/SKILL.md # Claude # Project-local mkdir -p .claude/skills/bitbucket && bbmd skill > .claude/skills/bitbucket/SKILL.md # Global mkdir -p ~/.claude/skills/bitbucket && bbmd skill > ~/.claude/skills/bitbucket/SKILL.md # Codex # Project-local mkdir -p .codex/skills/bitbucket && bbmd skill > .codex/skills/bitbucket/SKILL.md # Global mkdir -p ~/.codex/skills/bitbucket && bbmd skill > ~/.codex/skills/bitbucket/SKILL.md # Cursor # Project-local mkdir -p .cursor/skills/bitbucket && bbmd skill > .cursor/skills/bitbucket/SKILL.md # Global mkdir -p ~/.cursor/skills/bitbucket && bbmd skill > ~/.cursor/skills/bitbucket/SKILL.md

I'm so tired to have 20 folders with AI stuff...

You can have multiple accounts configured. This may be useful if you want AI to use different account for some tasks, like posting PR reviews or similar. The accountnameis just a label.

bbmd auth add \ --name user \ --default \ --token-type Bearer|Basic \ --token-value "<token>"

SeeBitbucket Access Tokensfor more details on creating tokens.

Note: If you already haveatlassian-accounts.json, just copy it to ~/.atlacp/accounts.json as follows:

cp your/path/to/atlassian-accounts.json ~/.atlacp/accounts.json

- bbmd auth status- list configured Atlassian accounts with redacted tokens.
- bbmd auth add- add or replace an account in the local accounts file.
- bbmd auth remove- remove an account by name.
- bbmd auth set-default- choose the default account.
- bbmd pr create- create a pull request.
- bbmd pr read- get pull request details.
- bbmd pr update- update pull request title, description, or draft state.
- bbmd pr approve- approve a pull request.
- bbmd pr request-changes- remove approval / request changes.
- bbmd pr merge- merge a pull request.
- bbmd pr diffstat- list changed files summary for a pull request.
- bbmd pr diff- get raw diff text.
- bbmd pr add-comment- add a general or inline pull request comment.
- bbmd pr list-comments- list pull request comments.
- bbmd pr resolve-comment- resolve a pull request comment thread.
- bbmd pr list-tasks- list pull request tasks.
- bbmd pr create-task- create a pull request task.
- bbmd pr update-task- update a pull request task.
- bbmd file content- get file content at a commit.

- bitbucket_add_pr_comment- add a comment to a pull request.
- bitbucket_approve_pr- approve a pull request.
- bitbucket_create_pr- create a pull request.
- bitbucket_create_pr_task- create a task on a pull request.
- bitbucket_get_file_content- get file content from a repository at a specific commit.
- bitbucket_get_pr_diff- get the diff of a pull request.
- bitbucket_get_pr_diffstat- get the diffstat of a pull request.
- bitbucket_list_pr_comments- list pull request comments.
- bitbucket_list_pr_tasks- list tasks on a pull request.
- bitbucket_merge_pr- merge a pull request.
- bitbucket_read_pr- read a pull request.
- bitbucket_resolve_pr_comment- resolve a pull request comment thread.
- bitbucket_request_pr_changes- request changes on a pull request.
- bitbucket_update_pr- update a pull request.
- bitbucket_update_pr_task- update a task on a pull request.

- HTTP athttp://localhost:8080.
- SSE athttp://localhost:8080/sse.
- STDIO viabbcp stdio.

Cursor MCP config (.cursor/mcp.json) may look like this for STDIO transport:

{ "mcpServers": { "Bitbucket": { "command": "bbcp", "args": ["stdio"] } } }
{ "mcpServers": { "Bitbucket": { "url": "http://localhost:8080" } } }

Once configured, send a prompt similar to:

Check titbucket pull request https://bitbucket.org/workspace/repo-slug/pull-requests/123

You should see a response with PR details.

Please review the official documentation:

- 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.

- Go tohttps://id.atlassian.com/manage-profile/security/api-tokens
- Create a new token, with at least below scopes:

read:account read:issue:bitbucket read:me read:pipeline:bitbucket read:project:bitbucket read:pullrequest:bitbucket read:repository:bitbucket read:runner:bitbucket read:snippet:bitbucket read:user:bitbucket write:issue:bitbucket write:pullrequest:bitbucket
echo -n "<your-email>:<your-api-token>" | base64
bbmd auth add \ --name user \ --default \ --token-type Basic \ --token-value "<base64-email-colon-api-token>"

If you plan your AI agent to operate as a bot, best option is to create "Access token" instead of "User API token".

- Go your repository or workspace settings, click on "Access tokens"
- Create a new token with below permissions:

pullrequest pipeline repository:write repository pullrequest:write
bbmd auth add \ --name bot \ --token-type Bearer \ --token-value "<your-bot-api-token>"

Please seeCONTRIBUTING.mdfor more details.

Perform queries and entity operations in your Fibery workspace.

Keep teams & agents coordinated automatically

Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.

A universal remote MCP server that connects to popular productivity tools such as Notion, Monday, AirTable, and many more.

advanced-math-mcp — MCP server for linear algebra, calculus, and symbolic math. 17 tools with a unified evaluate() expression engine. Supports matrices, eigenvalues, SVD, integrals, limits, derivatives, and more.

The Outcome Backcasting MCP is a strategic planning tool that helps you work backwards from a desired future outcome to identify the specific steps, resources, and dependencies needed to achieve your goals. Unlike traditional forward planning, backcasting starts with your end goal and creates a reverse roadmap to get there.

About A repo-native task graph as plain Markdown files, served to AI agents over MCP and to humans over a clean web UI .

Integrate ClickUp with AI applications to manage tasks, spaces, lists, and folders.

Interact with the ClickUp API to manage tasks, lists, and spaces, automating project planning and workflows.

Integrate AI assistants with ClickUp for productivity and project management.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.