Modifies an existing work item's fields and properties. Use this tool when you need to: - Change the status or state of a work item - Reassign work to a different team member - Update the description or details of a requirement - Modify effort estimates or priority levels - Add or change classifi...
AI agents use update_work_item to create or update resources in MCP Azure DevOps Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Azure DevOps Server environment.
This tool creates or modifies data reversibly without deleting or destroying information, placing it in the Write category. Severity is medium because misuse could disrupt team workflows, reassign work inappropriately, or corrupt work item metadata, but changes can be reverted. Confidence is high because the description clearly documents modification capabilities without irreversible data loss.
From the tool's definition Tool description states it 'Modifies an existing work item's fields and properties' and explicitly lists reversible operations: 'Change the status or state', 'Reassign work', 'Update the description', 'Modify effort estimates', 'Add or change classification'.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access update_work_item gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Azure DevOps Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_work_item:
{
"version": "1",
"default": "deny",
"tools": {
"update_work_item": {
"limits": [
{
"counter": "update_work_item_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} update_work_item stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Modifies an existing work item's fields and properties. Use this tool when you need to: - Change the status or state of a work item - Reassign work to a different team member - Update the description or details of a requirement - Modify effort estimates or priority levels - Add or change classification (area/iteration) - Update any field supported by the work item type IMPORTANT: This tool updates the work item directly in Azure DevOps. Changes will be immediately visible to all users with access to the work item and will trigger any configured notifications or workflows. You must specify at least one field to update. Args: id: The ID of the work item to update fields: Optional dictionary of field name/value pairs to update project: Optional project name or ID title: Optional new title for the work item description: Optional new description state: Optional new state assigned_to: Optional user email to assign to iteration_path: Optional new iteration path area_path: Optional new area path story_points: Optional new story points value priority: Optional new priority value tags: Optional new tags as comma-separated string Returns: Formatted string containing the updated work item details with all current field values, formatted as markdown. It is categorised as a Write tool in the MCP Azure DevOps Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Azure DevOps Server MCP server in PolicyLayer and add a rule for update_work_item: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Azure DevOps Server. Nothing to install.
update_work_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_work_item rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update_work_item. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update_work_item is provided by the MCP Azure DevOps Server MCP server (vortiago/mcp-azure-devops). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 MCP Azure DevOps Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 MCP Azure DevOps Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.