AI agents use update_issue_labels to create or update resources in Linear — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linear environment.
The tool modifies issue labels, which is a Write operation—it creates or modifies data reversibly. It does not delete data (not Destructive), does not execute arbitrary code (not Execute), does not move money (not Financial), and is not a Read operation since it has side effects.
From the tool's definition Tool name 'update_issue_labels' and description 'Update the labels of an existing issue' indicate modification of issue metadata. This is a reversible operation that changes issue state without deleting data.
Attacks that exploit this kind of access
Update the labels of an existing issue in Linear. It is categorised as a Write tool in the Linear MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Linear MCP server in PolicyLayer and add a rule for update_issue_labels: 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 Linear. Nothing to install.
update_issue_labels 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_issue_labels 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_issue_labels. 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_issue_labels is provided by the Linear MCP server (mkusaka/mcp-server-linear). 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 →