AI agents call linear_get_my_issues to retrieve information from MCP-GET without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing data (issues assigned to the user) from Linear without creating, modifying, or deleting anything. It is a simple query operation with no destructive or state-changing effects. The severity is low because unauthorized access to one's own task list poses minimal risk compared to other potential tool misuses.
From the tool's definition Tool name 'linear_get_my_issues' and description 'Get recent issues assigned to me from Linear' indicate a retrieval operation with no side effects. The verb 'Get' and lack of any modification language confirm read-only behavior.
Attacks that exploit this kind of access
Get recent issues assigned to me from Linear. It is categorised as a Read tool in the MCP-GET MCP Server, which means it retrieves data without modifying state.
Register the MCP-GET MCP server in PolicyLayer and add a rule for linear_get_my_issues: 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 MCP-GET. Nothing to install.
linear_get_my_issues 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_get_my_issues 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_get_my_issues. 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_get_my_issues is provided by the MCP-GET MCP server (kennethdsheridan/mcp-get). 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 →