AI agents call remarkable_canvas to retrieve information from reMarkable MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without an explicit description, classification relies on context. The tool name suggests viewing or retrieving canvas data (document/drawing content) from the tablet. The server's stated purpose emphasizes reading and extraction rather than modification.
From the tool's definition Tool name 'remarkable_canvas' with empty description. Based on sibling tools and server description focusing on 'read documents, browse files, extract text and OCR', this appears to be a read operation for accessing canvas/document content from the reMarkable…
Documented attack patterns abuse exactly the kind of access remarkable_canvas gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and reMarkable MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for remarkable_canvas:
{
"version": "1",
"default": "deny",
"tools": {
"remarkable_canvas": {}
}
}remarkable_canvas is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
remarkable_canvas. It is categorised as a Read tool in the reMarkable MCP Server MCP Server, which means it retrieves data without modifying state.
Register the reMarkable MCP Server MCP server in PolicyLayer and add a rule for remarkable_canvas: 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 reMarkable MCP Server. Nothing to install.
remarkable_canvas 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 remarkable_canvas 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 remarkable_canvas. 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.
remarkable_canvas is provided by the reMarkable MCP Server MCP server (pypi:remarkable-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from reMarkable MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 reMarkable MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.