This record as markdown: /tools/linear/update-issue.md
What update_issue does on Linear
AI agents use update_issue 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | — | The issue ID |
cycle | string | — | The cycle name, number, or ID |
links | array | — | Array of link objects to attach to the issue. Each object must contain a valid `url` and a non-empty `title`. |
state | string | — | The issue state type, name, or ID |
title | string | — | The issue title |
labels | array | — | Array of label names or IDs to set on the issue (you can use label names directly, no need to look up IDs) |
dueDate | string | — | The due date for the issue in ISO format |
project | string | — | The project name or ID to add the issue to |
assignee | string | — | The assignee name, displayName, or ID to assign |
delegate | string | — | The agent name, displayName, or ID to delegate |
estimate | number | — | The numerical issue estimate value |
parentId | string | — | The parent issue ID, if this is a sub-issue |
Parameters from the server's own tool schema.
Why update_issue is rated Medium
This tool modifies an existing issue entity in Linear, which is a reversible operation. Updates can typically be undone or corrected with subsequent edits. This places it in the Write category rather than Destructive (which would be for deletion/purging).
From the tool's definition Tool name 'update_issue' and description 'Update an existing Linear issue' indicate modification of existing data without deletion or irreversible destruction.
Risk signalsAccepts URL/endpoint input (links[].url) · High parameter count (16 properties)
Attacks that exploit this kind of access
The rule that runs update_issue safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Linear, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_issue, this is the rule to start with:
update_issue stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Linear, apply this rule, and every update_issue call is checked against it from then on.
Questions about update_issue
Update an existing Linear issue. 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.
update_issue accepts 12 parameters: id, cycle, links, state, title, labels, dueDate, project, assignee, delegate, estimate, parentId. The full parameter table on this page comes from the server's own tool schema.
Register the Linear MCP server in PolicyLayer and add a rule for update_issue: 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 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 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. 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 is provided by the Linear MCP server (@linear-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Linear, and thousands of servers like it.
This server
Across the catalogue