Remove a relationship between work items
AI agents call remove_work_item_relation to permanently remove resources in Azure DevOps MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a relationship is destructive because it irreversibly deletes metadata (the link itself) that connects two work items. While the work items themselves remain, the relationship data is permanently lost.
From the tool's definition Tool name includes 'remove' and description states 'Remove a relationship between work items' — this irreversibly deletes a relational link between work items, which cannot be undone without re-creating the relationship.
Attacks that exploit this kind of access
Remove a relationship between work items. It is categorised as a Destructive tool in the Azure DevOps MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Azure DevOps MCP Server MCP server in PolicyLayer and add a rule for remove_work_item_relation: 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 MCP Server. Nothing to install.
remove_work_item_relation is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_work_item_relation 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 remove_work_item_relation. 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.
remove_work_item_relation is provided by the Azure DevOps MCP Server MCP server (jaybird-us/azure-devops-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 →