Azure DevOps MCP Server

Microsoft's Azure DevOps MCP server enables AI agents to interact with Azure Boards work items, build pipelines, pull requests, and Git repositories. It equips agents to automate sprint planning, update issue statuses, track CI/CD pipeline runs, and review repository pull requests across enterprise Azure DevOps projects.

Start for free

Benefits with Ory + Azure DevOps MCP Server

Microsoft's Azure DevOps MCP server lets your agents work across Azure Boards, Repos, Pipelines, and wikis, from reading work items to creating pull requests and running builds. In a single organization that can span many projects and teams. Ory Agent Security lets planning agents read work items while code and pipeline changes stay with the agents you approve, and every tool call is tied to the user behind it.

View on GitHub

Use Cases

— 01 use case

Agent IAM

Reviewers read at Read, planning agents edit at Write knowing it can commit files, pipeline work stays at Admin, and Block covers the rest.

Explore Agent IAM

Core Functionality

— 04 capabilities

Read, write, admin, or no access
Ory Agent Security classifies every tool on the Azure DevOps MCP server as read, write, or admin, so you can give each user, team, or agent type only the level it needs: read for planning and reporting agents, write for agents that update work items and contribute code, admin for a release agent, and no access for agents with no role in your delivery process.
Enforced before execution
Ory Agent Security checks each tool call against the user, the agent acting for them, and any sub-agent inside the agent harness, so a denied pipeline run stops before it reaches Azure DevOps, with nothing to roll back and no gateway to deploy.
Observe, then enforce
Observe mode shows which agents touch boards, repos, and pipelines and on whose behalf without blocking anything, so you can apply Ory's pre-built policy for the Azure DevOps MCP server and enforce it on your own schedule.
Complete audit trail
Every allow and deny decision on the Azure DevOps MCP server streams to your SIEM through OpenTelemetry with the user, agent, and action attached, so you can show which agent started a pipeline or changed code, and for whom.