Is this an official Bitbucket MCP server?

No. It is Memtro's MCP server with Memtro's Bitbucket connector behind it: the connector reads Bitbucket through its API with the credentials you connect on Dashboard → Connections, and Bitbucket publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Bitbucket?

Only when you ask, and only what it has been granted: comment on a pull request, on the whole request or inline on one file and line; approve a pull request, take that approval back, or request changes; commit files to a branch as one commit, starting the branch from another when it is new; open a pull request from a branch that is already on Bitbucket; change a pull request's title, description, destination branch or draft state, or decline it; merge a pull request, choosing the strategy and whether the source branch goes. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Engineering and operations

Bitbucket MCP server

Bitbucket in any MCP client, through Memtro: Bitbucket does not publish this server. Memtro's Bitbucket connector reads Bitbucket through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Bitbucket Cloud: list repositories, search pull requests and read them with comments, approvals and changed files, browse commits, read or search code, and inspect Pipelines runs with failed-step logs; can also commit files to a branch, open a pull request, change it, merge it, comment on one (inline on a file and line) and record an approval or a request for changes when you ask.

Reads

bitbucket_repositoriesList Bitbucket repositories, most recently updated first: in one workspace…
bitbucket_pull_requestsSearch pull requests of one repository by state (open by default, or merged/declined/all), title text, source/destination branch…
bitbucket_commitsRecent commits of a repository, newest first, on the main branch or a given branch/tag/sha, optionally only those touching a path.
bitbucket_codeRead or search code.
bitbucket_pipelinesRecent Bitbucket Pipelines runs of a repository, newest first, optionally for one branch or only failed/successful runs.

Acts, when you ask

These change something in Bitbucket. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

bitbucket_comment_prComments on a Bitbucket pull request, either on the request as a whole or inline on one file and line — the inline form, path plus line…
bitbucket_approve_prRecords a review verdict on a Bitbucket pull request: approve it, take that approval back, request changes, or withdraw a request for changes.
bitbucket_commit_filesWrites files to a branch of a Bitbucket repository as one commit — this is the tool that actually changes code.
bitbucket_create_prOpens a pull request from a branch that is already on Bitbucket.
bitbucket_update_prChanges an open Bitbucket pull request — its title, its description, the branch it targets, whether merging it takes the source branch with it…
bitbucket_merge_prMerges a Bitbucket pull request.

Connect it

First connect Bitbucket on Dashboard → Connections, then add Memtro to your client once. The Bitbucket tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Bitbucket connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› Which pull requests in acme/web are open and unapproved?
› What did PR 142 change and who requested changes?
› Why did the last pipeline on main fail for the checkout service?
› Show the recent commits touching src/billing
› Read bitbucket-pipelines.yml from the develop branch

Questions

Is this an official Bitbucket MCP server?: No. It is Memtro's MCP server with Memtro's Bitbucket connector behind it: the connector reads Bitbucket through its API with the credentials you connect on Dashboard → Connections, and Bitbucket publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in Bitbucket?: Only when you ask, and only what it has been granted: comment on a pull request, on the whole request or inline on one file and line; approve a pull request, take that approval back, or request changes; commit files to a branch as one commit, starting the branch from another when it is new; open a pull request from a branch that is already on Bitbucket; change a pull request's title, description, destination branch or draft state, or decline it; merge a pull request, choosing the strategy and whether the source branch goes. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.