Returns tldraw
AI agents call read_diagram_guide to retrieve information from tldraw MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries diagram information from the tldraw canvas. It performs a read-only operation that fetches data without creating, modifying, deleting, or executing any operations. The tool fits the 'Read' category as it queries existing data. The severity is low because reading diagram data poses minimal risk—it cannot alter the canvas state, delete data, execute code, or cause financial harm.
From the tool's definition Tool name 'read_diagram_guide' and action of returning tldraw diagram data indicates retrieval of existing canvas/diagram information with no modification or side effects.
Attacks that exploit this kind of access
Returns tldraw. It is categorised as a Read tool in the tldraw MCP Server MCP Server, which means it retrieves data without modifying state.
Register the tldraw MCP Server MCP server in PolicyLayer and add a rule for read_diagram_guide: 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 Server. Nothing to install.
read_diagram_guide 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 read_diagram_guide 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 read_diagram_guide. 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.
read_diagram_guide is provided by the tldraw MCP Server MCP server (mihai-codes/tldraw-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 →