< Back to all integrations

Azure DevOps

Data & Infrastructure

Connect AI agents and workflows to Azure DevOps: work items and WIQL, boards, repos and pull requests, pipelines and releases, with service hooks.

Book a demo
[ Azure DevOps + engini ]

Azure DevOps for AI agents and workflows.

engini lets your AI agents and workflows work in Azure DevOps: query and create work items, update their state and add comments, read repos, commits and pull requests, run pipelines and read their results, and start a workflow the moment a service hook fires for a work item, a pull request or a build. Engineering stays in step with the service desk, the CRM and the business. Connect from Claude, ChatGPT or Cursor over MCP, from your code, or build in Workflow Studio.

MCPPython and TypeScript SDKCLIREST APIWorkflow Studio
Sign-inMicrosoft Entra ID, or a personal access token, for your organization
ReachProjects, work items, boards, repos, pull requests, pipelines and releases
TriggersService hooks, as work items, pull requests and builds change
[ 01 / What agents can do ]

What your agent can do in Azure DevOps. Every tool is one you allow or leave out.

The Azure DevOps tools in engini, grouped by what they change. Read tools are safe to hand out widely. Write and delete tools go only to the agents that need them.

Read

Run WIQL Query, Get Work Item

Find work items with a query and read their fields and history.

Read
Get Pull Requests, Get Commits

Read code changes and reviews.

Read
Get Pipeline Runs

Read builds and their results.

Read
Get Projects, Get Iterations

Read projects and sprints.

Read

Write

Create Work Item, Update Work Item, Add Comment

Open bugs and stories, move them and discuss them.

Write
Run Pipeline

Start a pipeline with parameters. Give it only to the agents that should.

Write
Create Pull Request Comment

Comment on a pull request.

Write

Any endpoint

Send API Request

Call any Azure DevOps REST API, with the sign-in added for you.

Any call

Triggers

Work Item Created, Work Item Updated

Work items added or changed.

Event
Pull Request Created or Merged, Build Completed

Code and pipeline events.

Event

A trigger starts a workflow, and a workflow can include an AI agent step. In Code, a trigger delivers the event to your own endpoint.

[ 02 / Connect your agent ]

Connect your AI agent to Azure DevOps. Four ways in, one set of permissions.

MCP

Claude, ChatGPT, Cursor

Create an MCP server in engini with your Azure DevOps connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.

MCP client setup →
SDK

Python and TypeScript

Hand your agent a toolset of Azure DevOps tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.

SDK guide →
CLI

For coding agents

The engini CLI connects Azure DevOps and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.

CLI guide →
REST API

Any language

Every Azure DevOps tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.

API reference →
MCP in four steps
In engini, connect Azure DevOps and create an MCP server with that connection and the tools this agent may use.
Claude: Settings, Connectors, Add custom connector, then paste the server address.
Cursor: add the address to .cursor/mcp.json. Claude Code: claude mcp add.
Sign in through engini when the client asks. The agent sees only the tools you chose.
Cursor, connected to Azure DevOps through engini
// .cursor/mcp.json: Cursor, connected to Azure DevOps through engini
{
"mcpServers": {
"engini-azure-devops": {
"url": "<your engini MCP server address>"
}
}
}

Create the MCP server in engini with your Azure DevOps connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.

Try asking your agent
“Which bugs reported by customers are still open this sprint?”
“Open a bug for the issue in this support ticket.”
“Which pull requests have been waiting for review over two days?”
“Did last night's release pipeline pass?”
“Move work item 4512 to Done and add a comment.”
“What shipped in the last release?”

Each request runs through the Azure DevOps tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.

[ 03 / What teams build ]

What teams build on Azure DevOps. Agents and workflows, across systems.

Support and engineering

Escalations tracked both ways

A ServiceNow, Zendesk or Freshservice ticket that needs a fix becomes an Azure DevOps bug, and the ticket gets a note when it ships.

ServiceNowZendeskAzure DevOps
Product

Feedback into the backlog

Feature requests from Gong calls and Intercom conversations become work items, tagged by account.

GongIntercomAzure DevOps
Engineering

Releases people hear about

When a release pipeline completes, release notes go to Teams and Confluence.

Azure DevOpsMicrosoft TeamsConfluence
Managers

Sprint status on request

An agent answers what is late, blocked or done. Its toolset holds read tools only.

Microsoft TeamsAzure DevOps

Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between Azure DevOps and another system engini connects is available.

[ 04 / Agent Policy ]

You decide what each agent may do in Azure DevOps. engini enforces it on every call.

Toolsets

Only the tools you allow

A toolset lists the Azure DevOps tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.

MCP servers

Scoped when you set them up

An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.

Identity

Whose permissions apply

Connect a person's own Azure DevOps account and engini acts as that person, with their Azure DevOps permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.

Credentials

Kept out of prompts

Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.

Audit

Every call on record

Every call lands in History and the audit log, which you can export or stream to your SIEM.

Environments

Test before production

Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.

SOC 2 Type IIISO 27001GDPRSecurity at engini →
[ 05 / Set up ]

Connect Azure DevOps in three steps. Then decide what each agent may do.

Step 01

Sign in to Azure DevOps

Add an Azure DevOps connection and sign in with Microsoft for your organization, or paste a personal access token with only the scopes the workflows need.

Step 02

Choose the tools

Add the connection to an MCP server or a toolset with only the tools each agent needs.

Step 03

Build or ask

Use the connection as a step in a workflow, or ask your agent to work in Azure DevOps from Claude, ChatGPT, Cursor or your own code.

[ 06 / Questions ]

Azure DevOps and engini. Straight answers.

Can an AI agent write to Azure DevOps, or only read?

Both. engini has tools to create and update work items, add comments, run pipelines and comment on pull requests. Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.

Does it work with Azure DevOps Server on premises?

Yes. Azure DevOps Server inside your network connects through the engini On-Prem Agent, with no inbound ports.

Does the agent act as me in Azure DevOps?

It acts as the Microsoft user or personal access token behind the connection, with that identity's project permissions. Every run is recorded under the person who started it.

Can a change in Azure DevOps start work?

Yes. Azure DevOps service hooks notify engini about work items, pull requests and builds. A trigger starts a workflow, and that workflow can include an AI agent step.

What if the tool I need is not listed?

Use Send API Request to call any Azure DevOps API endpoint through the same connection, and give it only to the agents that need it.