AI agents call linear_get_attachments to retrieve information from Linearapp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves (reads) attachments associated with an issue. The 'Get' operation is a standard read action that has no side effects—it does not create, modify, delete, execute code, or move money. The blast radius of misuse is minimal: an unauthorized read could expose file metadata or sensitive attachments, but cannot alter state or cause destructive operations.
From the tool's definition Tool name 'linear_get_attachments' and description 'Get attachments for an issue in Linear' indicate a retrieval operation with the verb 'Get', which queries existing data without modification.
Attacks that exploit this kind of access
Get attachments for an issue in Linear. It is categorised as a Read tool in the Linearapp MCP Server, which means it retrieves data without modifying state.
Register the Linearapp MCP server in PolicyLayer and add a rule for linear_get_attachments: 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 Linearapp. Nothing to install.
linear_get_attachments 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_attachments 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_attachments. 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_attachments is provided by the Linearapp MCP server (mcp-server-linearapp). 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 →