更新現有 Azure DevOps Work Item 的欄位 (例如狀態、指派對象)。
AI agents use update_work_item to create or update resources in Azure Devops — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Azure Devops environment.
The tool modifies work item data (status, assignee, etc.) in an existing resource. This is a Write operation because changes are reversible—fields can be updated again to restore prior state. Severity is medium because misuse could disrupt team workflows, corrupt work item state, or cause confusion by mass-reassigning tasks, but the changes are not permanent deletions and can be undone.
From the tool's definition Tool name 'update_work_item' and description confirms it updates existing Azure DevOps Work Item fields (e.g., status, assignee). This is a reversible modification operation.
Attacks that exploit this kind of access
更新現有 Azure DevOps Work Item 的欄位 (例如狀態、指派對象)。. It is categorised as a Write tool in the Azure Devops MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Azure Devops 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 Azure Devops. 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 Azure Devops MCP server (wuhuangjia/azure-devops-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →