A tool that gets comments from an issue in Linear
AI agents call get_comment to retrieve information from MCP Linear App without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Retrieving comments is a non-destructive query operation that returns existing data without modifying, creating, or deleting any content. This falls squarely under the Read category. Severity is low because unauthorized access to comments in a project management tool poses minimal risk—comments are typically visible to team members anyway, and reading them causes no damage.
From the tool's definition Tool is named 'get_comment' and described as retrieving comments from an issue in Linear. The verb 'get' and the read-only nature of comment retrieval confirm this is a data query operation with no side effects.
Attacks that exploit this kind of access
A tool that gets comments from an issue in Linear. It is categorised as a Read tool in the MCP Linear App MCP Server, which means it retrieves data without modifying state.
Register the MCP Linear App MCP server in PolicyLayer and add a rule for get_comment: 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 Linear App. Nothing to install.
get_comment 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 get_comment 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 get_comment. 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.
get_comment is provided by the MCP Linear App MCP server (zalab-inc/mcp-linear-app). 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 →