Read a tldraw canvas file (.tldr). Returns parsed JSON with pages and shapes. Base directory: ${TLDRAW_DIR}
AI agents call tldraw_read to retrieve information from tldraw MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though tldraw_read only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Read a tldraw canvas file (.tldr). Returns parsed JSON with pages and shapes. Base directory: ${TLDRAW_DIR}. It is categorised as a Read tool in the tldraw MCP MCP Server, which means it retrieves data without modifying state.
Register the tldraw MCP server in PolicyLayer and add a rule for tldraw_read: 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 tldraw MCP. Nothing to install.
tldraw_read 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 tldraw_read 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 tldraw_read. 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.
tldraw_read is provided by the tldraw MCP server (talhaorak/tldraw-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.