mcp-server-azure-devops
Enables interaction with Azure DevOps, including listing pipelines and runs, viewing logs and artifacts, collecting and normalizing security reports, and triggering pipelines with safety controls.
README
mcp-server-azure-devops
Azure DevOps MCP server aligned with your mcp-platform-gateway and @abhinav-dev/mcp-platform-kit pattern.
This server follows the same structure as mcp-server-git:
src/index.ts
src/config/env.ts
src/tools/registerAzureDevOpsTools.ts
src/azuredevops/azureDevOpsClient.ts
It does not use the raw MCP SDK directly. It extends McpServerBase from @abhinav-dev/mcp-platform-kit and registers tools through PlatformToolServer.
Capabilities
- List Azure DevOps pipelines
- List pipeline runs
- Get pipeline run details
- List pipeline logs
- Read pipeline log text
- List pipeline artifacts
- Download pipeline artifacts
- Collect security reports from artifacts
- Normalize Trivy, SARIF, Veracode-like JSON, and Aqua-like JSON reports
- Generate
normalized-vulnerability-report.json - Generate
copilot-fix-prompt.md - Trigger allowed pipelines with safety controls
Install
npm install
npm run build
Configure
Copy .env.example to .env.
MCP_NAME=azure-devops
MCP_VERSION=1.0.0
MCP_PORT=3005
MCP_SELF_URL=http://localhost:3005
GATEWAY_URL=http://localhost:3000
AZDO_ORG=your-organization
AZDO_PROJECT=your-project
AZDO_PAT=your-personal-access-token
AZDO_API_VERSION=7.1
AZDO_ENABLE_TRIGGER=false
AZDO_ALLOWED_PIPELINES=12,15,20
AZDO_ALLOWED_BRANCHES=refs/heads/main,refs/heads/dev
AZDO_DOWNLOAD_DIR=.azdo-downloads
AZDO_REPORT_DIR=.azdo-reports
Run
npm run dev
Important tools
azure_list_pipelines
azure_list_pipeline_runs
azure_get_pipeline_run
azure_list_pipeline_logs
azure_get_pipeline_log_text
azure_list_pipeline_artifacts
azure_download_pipeline_artifact
azure_collect_security_reports
azure_normalize_local_security_reports
azure_trigger_pipeline
Security report workflow
Recommended Azure Pipeline artifact layout:
security-reports/
trivy/
trivy-fs.json
trivy-image.json
veracode/
veracode-findings.json
aqua/
aqua-report.json
Then call:
{
"pipelineId": 12,
"runId": 345,
"artifactName": "security-reports"
}
using azure_collect_security_reports.
Output:
.azdo-reports/<pipelineId>/<runId>/normalized-vulnerability-report.json
.azdo-reports/<pipelineId>/<runId>/copilot-fix-prompt.md
Open copilot-fix-prompt.md in VS Code and ask GitHub Copilot to implement the fixes.
Pipeline trigger safety
Pipeline trigger is disabled by default.
Enable only after configuring allowed pipelines and branches:
AZDO_ENABLE_TRIGGER=true
AZDO_ALLOWED_PIPELINES=12,15,20
AZDO_ALLOWED_BRANCHES=refs/heads/main,refs/heads/dev
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。