Atlassian Bamboo MCP Server

Atlassian Bamboo MCP Server

Enables AI assistants to interact with Atlassian Bamboo CI/CD, allowing natural language queries to check build status, fetch logs, trigger builds, and manage deployments.

Category
访问服务器

README

Atlassian Bamboo MCP Server

CI NPM Version MIT licensed TypeScript MCP

A Model Context Protocol (MCP) server that brings Atlassian Bamboo CI/CD operations directly into AI assistants like Claude Code and Cursor.

❌ Without Bamboo MCP

Working with Bamboo CI/CD requires constant context switching:

  • ❌ Switching to browser to check build status
  • ❌ Manually navigating through Bamboo UI to find logs
  • ❌ Copy-pasting build keys and deployment IDs
  • ❌ No AI assistance for CI/CD troubleshooting

✅ With Bamboo MCP

Bamboo MCP brings your CI/CD operations directly into your AI workflow:

What's the status of the latest build for project MY-PROJECT?
Show me the deployment logs for deployment result 2661941325
Trigger a build for plan PROJ-PLAN with variable ENV=staging

No tab-switching, no manual navigation — just ask and get instant CI/CD insights.

Features

  • 26 tools covering all major Bamboo operations
  • Build logs with actual content (not just URLs)
  • Deployment logs with full output
  • Proxy support for corporate environments
  • TypeScript with full type safety

Installation

Prerequisites

From Source

git clone https://github.com/norus/atlassian-bamboo-mcp.git
cd atlassian-bamboo-mcp
npm install
npm run build

From npm

npm install -g bamboo-mcp-server

Configuration

The server requires these environment variables:

Variable Required Description
BAMBOO_URL Yes Base URL of your Bamboo server
BAMBOO_TOKEN Yes Personal access token
BAMBOO_PROXY No Proxy URL (e.g., http://proxy:8080)

Creating a Bamboo Token

  1. Log into Bamboo
  2. Go to ProfilePersonal access tokens
  3. Click Create token
  4. Give it a name and appropriate permissions
  5. Copy the token (you won't see it again)

Setup

<details> <summary><b>Claude Code</b></summary>

Run this command:

claude mcp add bamboo -- npx -y bamboo-mcp-server@latest

Or add to ~/.claude/settings.json:

{
  "mcpServers": {
    "bamboo": {
      "command": "npx",
      "args": ["-y", "bamboo-mcp-server@latest"],
      "env": {
        "BAMBOO_URL": "https://bamboo.example.com",
        "BAMBOO_TOKEN": "your-token"
      }
    }
  }
}

</details>

<details> <summary><b>Claude Desktop</b></summary>

Add to your config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "bamboo": {
      "command": "npx",
      "args": ["-y", "bamboo-mcp-server@latest"],
      "env": {
        "BAMBOO_URL": "https://bamboo.example.com",
        "BAMBOO_TOKEN": "your-token",
        "BAMBOO_PROXY": "http://proxy:8080"
      }
    }
  }
}

</details>

<details> <summary><b>Cursor</b></summary>

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "bamboo": {
      "command": "npx",
      "args": ["-y", "bamboo-mcp-server@latest"],
      "env": {
        "BAMBOO_URL": "https://bamboo.example.com",
        "BAMBOO_TOKEN": "your-token"
      }
    }
  }
}

</details>

<details> <summary><b>npx</b></summary>

BAMBOO_URL="https://bamboo.example.com" \
BAMBOO_TOKEN="your-token" \
npx bamboo-mcp-server

</details>

<details> <summary><b>Docker</b></summary>

Build the image

docker build -t bamboo-mcp-server .

Run with Docker

docker run -i --rm \
  -e BAMBOO_URL="https://bamboo.example.com" \
  -e BAMBOO_TOKEN="your-token" \
  -e BAMBOO_PROXY="http://host.docker.internal:8080" \
  bamboo-mcp-server

Proxy configuration

When using a proxy from Docker:

  • macOS/Windows: Use host.docker.internal to reach the host (e.g., http://host.docker.internal:8080)
  • Linux: Use --network host flag or the host's actual IP address

Use with Claude Desktop

{
  "mcpServers": {
    "bamboo": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "BAMBOO_URL=https://bamboo.example.com",
        "-e", "BAMBOO_TOKEN=your-token",
        "-e", "BAMBOO_PROXY=http://host.docker.internal:8080",
        "bamboo-mcp-server"
      ]
    }
  }
}

Docker Compose

services:
  bamboo-mcp:
    build: .
    environment:
      - BAMBOO_URL=https://bamboo.example.com
      - BAMBOO_TOKEN=${BAMBOO_TOKEN}
      - BAMBOO_PROXY=http://host.docker.internal:8080
    stdin_open: true

</details>

Available Tools

Server (2)

Tool Description
bamboo_server_info Get Bamboo server version and state
bamboo_health_check Check server health status

Projects (2)

Tool Description
bamboo_list_projects List all projects
bamboo_get_project Get project details by key

Plans (6)

Tool Description
bamboo_list_plans List all build plans
bamboo_get_plan Get plan details by key
bamboo_search_plans Search plans by name
bamboo_enable_plan Enable a build plan
bamboo_disable_plan Disable a build plan
bamboo_clone_plan Clone a build plan to a new plan

Branches (2)

Tool Description
bamboo_list_plan_branches List branches for a plan
bamboo_get_plan_branch Get branch details

Builds (7)

Tool Description
bamboo_trigger_build Trigger a build (supports variables)
bamboo_stop_build Stop a running build
bamboo_get_build_result Get specific build result
bamboo_get_latest_result Get latest build result
bamboo_list_build_results List build results with filters
bamboo_get_build_logs Get build log file URLs
bamboo_get_build_result_logs Get build logs with actual content

Queue (2)

Tool Description
bamboo_get_build_queue Get current build queue
bamboo_get_deployment_queue Get deployment queue status

Deployments (6)

Tool Description
bamboo_list_deployment_projects List deployment projects
bamboo_get_deployment_project Get deployment project details
bamboo_create_deployment_project Create a deployment project linked to a build plan
bamboo_get_deployment_results Get deployment results for environment
bamboo_get_deployment_result Get deployment result with logs
bamboo_trigger_deployment Trigger a deployment

Example Prompts

Show me all failed builds in the last 24 hours
What's blocking the deployment queue?
Get the logs for build PROJ-PLAN-123 and tell me why it failed
Trigger a build for MY-PROJECT with variable DEPLOY_ENV=staging
List all branches for plan MY-PLAN and their build status

Development

# Install dependencies
npm install

# Build
npm run build

# Run tests
npm test

# Run tests with coverage
npm run test:coverage

# Run locally
BAMBOO_URL="https://bamboo.example.com" \
BAMBOO_TOKEN="your-token" \
node dist/index.js

Troubleshooting

<details> <summary><b>Connection refused / timeout</b></summary>

  • Verify BAMBOO_URL is correct and accessible
  • If behind a proxy, set BAMBOO_PROXY
  • Check if your token has expired

</details>

<details> <summary><b>401 Unauthorized</b></summary>

  • Verify your BAMBOO_TOKEN is correct
  • Ensure the token hasn't expired
  • Check token permissions in Bamboo

</details>

<details> <summary><b>Tool not found in Claude</b></summary>

  • Restart Claude Code/Desktop after config changes
  • Verify the path to dist/index.js is absolute
  • Check Claude's MCP logs for errors

</details>

Security

  • No hardcoded secrets — all credentials via environment variables
  • Input validation — Zod schemas on all tool inputs
  • Proxy support — works in corporate environments
  • Read-heavy — most operations are read-only

For security issues, please report via GitHub Security tab.

License

MIT

Contributing

Contributions welcome! Please read our contributing guidelines before submitting PRs.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选