AI agents use ado_update_work_item to create or update resources in Mcp Azure — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Azure environment.
This tool creates or modifies data reversibly within Azure DevOps. Updating work items (changing status, fields, assignments, etc.) is a standard Write operation. It's reversible—changes can be undone or corrected. The severity is medium because misuse could cause workflow disruption or incorrect project state, but no data is permanently deleted and financial impact is unlikely without chaining to other tools.
From the tool's definition Tool name 'ado_update_work_item' and description 'Actualiza un Work Item existente en Azure DevOps' (Updates an existing Work Item in Azure DevOps) indicate modification of existing data.
Attacks that exploit this kind of access
Actualiza un Work Item existente en Azure DevOps. It is categorised as a Write tool in the Mcp Azure MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Azure MCP server in PolicyLayer and add a rule for ado_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. Nothing to install.
ado_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 ado_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 ado_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.
ado_update_work_item is provided by the Mcp Azure MCP server (soulberto/mcp-azure). 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 →