AI agents use link_work_items to create or update resources in Ado — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ado environment.
Based on the tool name alone, 'link_work_items' most likely creates associations between Azure DevOps work items. This is a Write operation as it modifies data (creates links) but is generally reversible (links can be removed). Confidence is lowered due to empty description. Severity is medium as misuse could create incorrect work item relationships affecting project tracking.
From the tool's definition Tool name 'link_work_items' suggests creating relationships/links between work items, which is a reversible write operation. Description is empty and uninformative.
Attacks that exploit this kind of access
link_work_items. It is categorised as a Write tool in the Ado MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ado MCP server in PolicyLayer and add a rule for link_work_items: 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 Ado. Nothing to install.
link_work_items 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 link_work_items 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 link_work_items. 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.
link_work_items is provided by the Ado MCP server (raboley/ado-mcp). 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 →