Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Azure DevOps MCP Server list my assigned PBIs for this sprint"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server for managing Azure DevOps work items — Product Backlog Items (PBIs), Tasks, Bugs — and their comments, directly from an MCP-compatible client such as Kiro, Claude Desktop, or Cursor.
Configured for the organization DigiFY2025 and project DIGI STD FY26.
Create, read, update PBIs
List your own unfinished work items
Flexible search/list with filters or raw WIQL
Add, list, update, delete comments on any work item
Automatic sprint detection based on the current date
Sensible defaults for area path and iteration path
Related MCP server: Azure MCP FastMCP Server
Node.js 18+ (uses the built-in fetch). See .nvmrc for the pinned version.
An Azure DevOps Personal Access Token (PAT) with Work Items (Read & Write) scope.
Install dependencies:
npm installCreate a .env file from the example and add your PAT:
cp .env.example .envAZURE_DEVOPS_PAT=your-personal-access-token-here
.envis git-ignored. Never commit your real PAT.
Run the server:
npm startAdd the server to your MCP client config (e.g. .kiro/settings/mcp.json):
{
"mcpServers": {
"azure-devops": {
"command": "node",
"args": ["/absolute/path/to/azure-devops-mcp/index.js"],
"env": {
"AZURE_DEVOPS_PAT": "your-personal-access-token-here"
}
}
}
}Tool | Description |
| Create a Product Backlog Item. Auto-detects the current sprint and defaults the area path. Supports title, description, acceptance criteria, assignee, area/iteration path, start/target dates, and a parent link. |
| Create a Task, optionally linked under a parent PBI. Supports title, description, assignee, area/iteration path, remaining work, activity, and priority. Auto-detects the current sprint. |
| Read full details of any work item by ID (PBI or Task), including parent/child relations. |
| Update fields of any existing work item (title, description, state, priority, dates, tags, etc.). Works for both PBIs and Tasks. |
| Delete any work item by ID. Moves to the Recycle Bin by default; set |
| List work items assigned to you (via the PAT) that are not Done/Closed/Removed. |
| Search/list work items using filters (text, state, assignee, iteration, area) or a raw WIQL query. |
Tool | Description | Parameters |
| Add a comment to a work item. |
|
| List all comments on a work item. |
|
| Edit an existing comment. |
|
| Delete a comment. |
|
Defined at the top of index.js:
ORG — Azure DevOps organization (DigiFY2025)
PROJECT — project name (DIGI STD FY26)
DEFAULT_AREA_PATH — default area path for new PBIs
SPRINT_LIST — sprint schedule used for automatic current-sprint detection
Authentication uses the AZURE_DEVOPS_PAT environment variable only; no tokens are hardcoded.
.env is git-ignored so your PAT stays local.
Treat your PAT like a password: scope it minimally and rotate it if exposed.
MIT
This server cannot be deployed
Crie épicos, features, histórias e tasks no Azure DevOps a partir de uma conversa.
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Remote MCP for Kanban AI boards—manage projects, tasks, and comments from AI tools.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
