AI agents call pylon_get_attachment to retrieve information from Pylon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only fetches and returns attachment metadata and provides a download URL; it does not create, modify, delete, or execute any operations. The action is purely informational retrieval, making it a Read category risk with low severity since attachment access depends on already having a valid attachment_id and appropriate permissions to that issue.
From the tool's definition The tool description states it retrieves 'attachment metadata by ID' and allows 'Download the file using the returned URL'. The verb 'Get' and the phrase 'retrieves... metadata' indicate a read-only operation with no side effects.
Attacks that exploit this kind of access
Get attachment metadata by ID. Use when you have an attachment_id from an issue message. Download the file using the returned URL. It is categorised as a Read tool in the Pylon MCP Server, which means it retrieves data without modifying state.
Register the Pylon MCP server in PolicyLayer and add a rule for pylon_get_attachment: 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 Pylon. Nothing to install.
pylon_get_attachment 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 pylon_get_attachment 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 pylon_get_attachment. 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.
pylon_get_attachment is provided by the Pylon MCP server (@customer-support-success/pylon-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 →