Bamboo MCP server

What the model can do

Atlassian Bamboo Data Center CI/CD: build plans, the latest and past build results with state, duration, tests, stages, labels and linked Jira issues, the build queue, deployment projects with their environments and what was deployed to each, and build agents; when you ask, can run a plan, continue or stop a build, comment on or label a result, create a release from a build, deploy a release to an environment, cancel a queued deployment, and enable or disable a plan.

Reads

• bamboo_list_plansBamboo build plans: key (PROJ-PLAN, what the build tools take), name, project, enabled, and whether building now.
• bamboo_latest_resultsThe latest build result of each top-level plan: state (Successful, Failed), when, how long, why it ran, test counts, revision and link.
• bamboo_plan_resultsBuild history of one plan (or one job, PROJ-PLAN-JOB): each result's number, state, when, duration, reason, tests and revision.
• bamboo_get_resultOne build result (PROJ-PLAN-42, or PROJ-PLAN-latest): state, timing, reason, tests, revision, each stage's state, labels…
• bamboo_build_queueBuilds waiting in Bamboo's queue: result key, plan, build number and why each was triggered.
• bamboo_deployment_projectsBamboo deployment projects with their environments (ids, names), and the build plan each releases from.
• bamboo_environment_deploymentsWhat was deployed to one Bamboo environment, newest first: release (version) name, state, life-cycle, when it started and finished, and why it ran.
• bamboo_agentsBamboo build agents: name, type (local, remote, elastic), whether enabled, active and busy.

Acts, when you ask

These change something in Bamboo. 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.

• bamboo_run_planQueues a build of a Bamboo plan (top-level plan key, not a job), which runs its build scripts on an agent…
• bamboo_continue_buildContinues a partially run Bamboo build (one stopped at a manual stage, or to re-run its failed jobs) by putting it back in the queue…
• bamboo_stop_buildStops a running or queued Bamboo job.
• bamboo_comment_buildAdds a comment to a Bamboo build result, shown to everyone who can see the plan.
• bamboo_label_buildAdds a label to a Bamboo build result (labels are lower-case words used to find and filter builds).
• bamboo_create_releaseCreates a release (deployment version) in a Bamboo deployment project from a successful build result, carrying that build's artifacts…
• bamboo_deployDeploys a release (version id) to a Bamboo environment (environment id) by queueing its deployment tasks, which change whatever that environment is…
• bamboo_cancel_deploymentRemoves a deployment from Bamboo's queue before it starts (by its deployment result id).
• bamboo_set_plan_enabledEnables or disables a Bamboo plan.

Connect it

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

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

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

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

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 Bamboo 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 plans are failing right now?
• › Which Jira issues are linked to the last build of the web app plan?
• › What was last deployed to the production environment, and when?
• › What is waiting in the build queue?
• › Run the nightly integration plan now.

Questions

Is this an official Bamboo MCP server?

No. It is Memtro's MCP server with Memtro's Bamboo connector behind it: the connector reads Bamboo through its API with the credentials you connect on Dashboard → Connections, and Bamboo 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 Bamboo?

Only when you ask, and only what it has been granted: run a build plan; continue a partially run build; stop a running job; comment on a build result; label a build result; create a release from a build; deploy a release to an environment; cancel a queued deployment; enable or disable a build plan. 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.

Other MCP servers · Engineering and operations

• GitHub MCP server
• AWS CloudWatch MCP server
• Sentry MCP server
• ServiceNow MCP server
• Okta MCP server
• Twilio MCP server