Connect your AI to Azure DevOps
Azure Boards is the destination when the backlog lives in Azure DevOps rather than GitHub. Authentication is a personal access token sent as an HTTP Basic credential, held server-side. Two API quirks shape every pipe here: WIQL answers a query with bare work item ids and no fields, and the batch endpoint refuses collection reads. That is why reading the board takes two pipes rather than one.
The credential never enters the model context: it lives in the FlurryPORT secret store, deliveries are signed server-side, and every send returns a receipt your agent can quote.
- Auth model
- static_header
- Suggested secret
AZURE_DEVOPS_PAT- Scopes
- A Personal Access Token with Work Items (Read & write). The stored value is the HTTP Basic credential: base64 of a colon followed by the PAT (run: printf ':YOUR_PAT' | base64). The catalog never sees the raw PAT.
- Provider docs
- https://learn.microsoft.com/rest/api/azure/devops/wit/work-items/create
Recipes for Azure DevOps
Create and update Azure DevOps work items in one batched pipe: priority, state, tags, and sprint included.
Query Azure DevOps work items with WIQL and read the matching ids back, without your AI ever holding the PAT.
Read fields for a batch of Azure DevOps work items by id: title, state, tags, priority, iteration.
Let your AI file Azure DevOps work items (bugs, tasks) the model never holds credentials for.