Azure DevOps MCP for AI. Track build history and manage project backlog from your agent.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
Azure DevOps MCP connects your agent directly into your CI/CD workflow. You can check project status, track work items, monitor build history, and manage repositories across any Azure DevOps organization without leaving your client.
What your AI can do
List builds
Gets a list of recent build executions, showing their completion status and who triggered them.
List pipelines
Retrieves the definitions and current status for all defined CI/CD pipelines in your project.
List projects
Retrieves metadata for every active and archived project in the entire organization.
List and retrieve metadata for every project in an organization or list specific teams within a project.
Query recent work items, allowing you to track bugs, stories, and tasks across your team’s backlog.
List all available Git repositories within a project for code source tracking.
View defined CI/CD pipelines and fetch the history, status, or metadata of recent build executions.
Ask an AI about this
Waiting for input…
Azure DevOps: 6 Tools for CI/CD Management
These tools let you programmatically inspect every core component of your Azure DevOps setup—from project definitions to individual user stories.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Azure DevOps on VinkiusList Builds
Gets a list of recent build executions, showing their completion status and who triggered them.
List Pipelines
Retrieves the definitions and current status for all defined CI/CD pipelines in your...
List Projects
Retrieves metadata for every active and archived project in the entire organization.
List Repositories
Shows all Git repositories linked to a project, helping you pinpoint code storage...
List Project Teams
Lists all team structures within a specific project to understand who owns which...
List Work Items
Queries and lists recent work items, such as bugs or user stories, based on filters like status or assignee.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Azure DevOps, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Azure DevOps. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 6 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The current process of tracking project status is fragmented.
Today, checking a single feature's readiness requires jumping between three different tabs: the Project Dashboard for work items, the Pipelines section for build history, and then manually navigating to the code repositories. You copy IDs from one screen, paste them into another, and cross-reference dates yourself.
With this MCP, you tell your agent what you need—'Is Feature X deployable?' The system handles the complex calls across multiple tools in the background. It delivers a single answer based on `list_work_items`, `list_pipelines`, and `list_builds`.
Project Oversight with Azure DevOps MCP
Previously, to get an organizational overview, you had to manually request lists of all projects and then ask a team lead for the current assignments. This involved multiple emails and waiting for status updates.
Now, your agent runs `list_projects` to give you the full inventory. Then, with one prompt, it can run `list_project_teams`, giving you an immediate organizational map. It's that simple.
What your AI can actually do with this
You need visibility into the entire software development lifecycle—from story definition to deployment artifact. This MCP lets your AI client query everything in your Azure DevOps environment through natural conversation. You can list all projects in an organization or drill down into specific teams and repositories within a project. Need to know if a feature is blocked? Query work items to see status changes, track bugs, or check user stories.
Want to know if the code deployed correctly? List pipelines and review recent build history right from your agent. If you're using Vinkius, this MCP gives you instant access to all those operational details, letting your agent act as a centralized dashboard for your entire DevOps setup.
019dd0c0-0d4b-7356-9046-d453ae059986 Here's how it actually works
The bottom line is you manage your DevOps ecosystem by talking to it, not by clicking through dashboards.
Subscribe to this MCP and provide your Azure DevOps Organization name and Personal Access Token (PAT).
Connect your preferred AI agent client. The connection authenticates your permissions across the organization.
Ask your agent a direct question, like 'What was the status of the last build for Project X?' Your agent executes the necessary tool call and reports the real-time data.
Who is this actually for?
This MCP is critical for developers who are tired of context switching between the portal and their chat interface. It's built for the ops engineer who needs immediate build status checks at 2 am, or the product owner who needs a real-time health check on backlog progress.
Monitoring build history and managing repositories directly from the agent. They use this to troubleshoot why a deployment failed.
Quickly checking pipeline statuses or verifying work item details before starting development on a specific feature.
Getting an instant view of project health by querying the status and progress of user stories across multiple projects.
What Changes When You Connect
Cut down on manual checking. Instead of navigating to the pipeline dashboard, you ask your agent about list_pipelines status directly in your chat.
Stop hunting for code sources. You can use list_repositories to quickly see all linked Git repos without leaving your IDE or terminal.
Get a single view of project health. Use list_projects and then follow up with list_work_items to check the backlog status in one conversation flow.
Understand team structure instantly. Running list_project_teams gives you an overview of who is assigned to what, removing coordination guesswork.
Accelerate debugging. If a build fails, your agent can use list_builds to pull up the failure history and tell you exactly when it happened.
See it in action
The Feature Freeze Check
A Product Owner needs to know if three key features are ready for release. They ask their agent, which then uses list_work_items to check the status of all related stories and flags any that are stuck in 'Review' status.
The Deployment Failure Investigation
A DevOps Specialist gets an alert. They ask their agent, which immediately uses list_builds and list_pipelines. The agent provides the failure ID and suggests checking the repository via list_repositories for recent commits.
The Team Restructure Audit
A manager needs to know who is on which team after a merger. They ask their agent, running list_project_teams, getting an immediate breakdown of organizational assignments across the entire project set.
Initial Project Assessment
A new developer joins and needs to know what code base they should look at. They use list_projects first, then drill down with list_repositories on the correct project ID to find the starting point.
The honest tradeoffs
Over-relying on UI navigation
Opening the Azure DevOps portal, clicking through Build -> Pipelines -> History -> Project Name. This takes five clicks and forces context switching.
Connect this MCP to your agent client. Instead of navigating, simply ask: 'What was the status of the last build for my project?' The tool handles the pathing via list_builds.
Forgetting necessary context
Asking 'Show me the bug' without specifying the project or team, leading to vague results or API errors.
Always provide project scope. First use list_projects to confirm the ID, then use that ID when querying work items via list_work_items.
Mixing up code and task tracking
Thinking that checking a user story status (list_work_items) automatically shows if the associated code was merged to the main branch.
These are separate concerns. Check the work item first, then use list_pipelines to confirm the required build passed before closing the task.
When It Fits, When It Doesn't
Use this MCP if your pain point is visibility across the entire SDLC: you need to correlate status (work items) with deployment state (builds/pipelines). Don't use it if you just need basic documentation lookups, like checking a specific resource ID that isn't tracked in Azure DevOps. If you only need to read static documents or view raw Git commit logs without relation to the workflow, an alternative API connection might be better. However, if your goal is understanding 'Is this feature ready to ship?', this MCP—with its ability to chain together data from list_work_items, list_pipelines, and list_builds—is the right tool.
Questions you might have
How do I use list_work_items in Azure DevOps? +
You query this tool by specifying filters like status, assignee, or type (bug/story). This lets you pull a targeted list of items without having to manually filter the dashboard.
What is the difference between list_pipelines and list_builds? +
The pipelines define the workflow steps. The builds track the actual, executed history of those workflows. You need list_pipelines to see how it runs, and list_builds to see if the last run succeeded.
Can I find all my code locations using list_repositories? +
Yes. This tool queries every Git repository attached to a project, giving you an inventory of where the source code is stored within your organization's scope.
Does this MCP help with team coordination? (list_project_teams) +
It lists all defined teams and their members for a given project. This helps you understand the operational structure without needing to contact anyone.
What authentication method does the MCP use when running list_projects? +
It requires a Personal Access Token (PAT) paired with your Azure DevOps organization URL. This PAT must have read scope permissions for Project and Work Item services to ensure the tool can properly enumerate all available projects.
Can I filter my results when calling list_pipelines by environment? +
Yes, you specify the desired environment name or ID as part of the query parameters. This allows your agent to narrow down pipeline searches and focus only on builds relevant to staging or production environments.
If I run list_builds and receive an error, what does that usually mean? +
An error often means the provided PAT lacks build history read permissions. You might need to check your token scope or ensure the project ID used in the query is accurate for the intended build.
Does running list_work_items frequently across many projects cause rate limits? +
The MCP manages standard API call throttling, but excessive requests in a short period could trigger limits. For large-scale data retrieval, it's better to batch your work item queries or schedule them.
Can I see if a build pipeline failed via the AI? +
Yes! Use the list_builds tool and provide the Project ID. Your agent will retrieve the history of recent executions, including their final status (succeeded, failed, inProgress).
How do I list the Git repositories for a project? +
Run the list_repositories query with your Project ID. The agent will return all Git repositories associated with that project in your Azure DevOps account.
Is it possible to see recent bugs or tasks assigned to a project? +
Absolutely. Use the list_work_items tool. Your agent will retrieve a list of recent work items, including bugs, tasks, and stories, for the specified project.
We've already built the connector for Azure DevOps. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 6 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.