AI agents call linear_getNotifications to retrieve information from Linear without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves notification data for the authenticated user. It performs a query operation that reads existing data without creating, modifying, deleting, or executing any external actions. The blast radius of misuse is minimal — an attacker could only view the user's own notifications, which are already visible to that user in the normal UI. No data integrity, financial, or operational impact is possible.
From the tool's definition Tool name is 'linear_getNotifications' and description states 'Get notifications for the current user' — this is a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access linear_getNotifications gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Linear, and nothing reaches the server without passing your rules. This is the rule we recommend for linear_getNotifications:
{
"version": "1",
"default": "deny",
"tools": {
"linear_getNotifications": {}
}
}linear_getNotifications is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get notifications for the current user. It is categorised as a Read tool in the Linear MCP Server, which means it retrieves data without modifying state.
Register the Linear MCP server in PolicyLayer and add a rule for linear_getNotifications: 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.
linear_getNotifications is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the linear_getNotifications 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_getNotifications. 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_getNotifications is provided by the Linear MCP server (tacticlaunch/mcp-linear). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 182 Linear tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
182 Linear tools catalogued and risk-classified — across an index of 42,500+ MCP servers.