AI agents call download_pdf to retrieve information from Remark without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and exports an existing PDF document from a connected device, returning it as base64-encoded data. There is no modification, deletion, execution, or financial impact. It is a read-only operation that queries and retrieves data. The low severity reflects that misuse would only expose information already on the device, not cause irreversible changes or execute arbitrary code.
From the tool's definition Tool description explicitly states 'Download a document from the reMarkable tablet as a PDF' — this retrieves/exports data. The server description confirms the purpose is 'to browse and read documents' with 'no side effects' expected.
Attacks that exploit this kind of access
Download a document from the reMarkable tablet as a PDF, returned as base64-encoded data. It is categorised as a Read tool in the Remark MCP Server, which means it retrieves data without modifying state.
Register the Remark MCP server in PolicyLayer and add a rule for download_pdf: 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 Remark. Nothing to install.
download_pdf 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 download_pdf 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 download_pdf. 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.
download_pdf is provided by the Remark MCP server (robbogd76/remark-mcp). 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 →