AI agents use linear_action to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
first | number | — | Number of results to return (default 25). |
query | string | — | Search term (for search_issues). |
title | string | — | Issue title (for create_issue). |
action | string | Yes | Action: list_issues, create_issue, get_project, list_teams, search_issues. |
api_key | string | Yes | Linear API key. |
team_id | string | — | Team ID (required for create_issue, optional filter for list_issues). |
priority | number | — | Priority: 0 (none), 1 (urgent), 2 (high), 3 (medium), 4 (low). |
state_id | string | — | Workflow state ID. |
project_id | string | — | Project ID (for get_project). |
assignee_id | string | — | Assignee user ID. |
description | string | — | Issue description. |
Parameters from the server's own tool schema.
The tool performs both read operations (list, search, get) and write operations (create issues). By the severity hierarchy, Write is more severe than Read. Creating issues is reversible (issues can be deleted or modified later), so it does not qualify as Destructive.
From the tool's definition Tool description explicitly states 'create issues' alongside read operations like 'list and search issues' and 'get project details'. Creating issues modifies data in the Linear project management system.
Risk signalsAccepts freeform code/query input (query) · Handles credentials or secrets (api_key) · High parameter count (11 properties)
Attacks that exploit this kind of access
Interact with the Linear GraphQL API: list and search issues, create issues, get project details, and list teams. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
linear_action accepts 11 parameters: first, query, title, action, api_key, team_id, priority, state_id, project_id, assignee_id, description. Required: action, api_key. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for linear_action: 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 UnClick. Nothing to install.
linear_action 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 linear_action 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 linear_action. 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.
linear_action is provided by the UnClick MCP server (@unclick/mcp-server). 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 →