Read the current state of the diagram (nodes, edges, positions). Use this to observe changes the user made in the editor.
AI agents call get_diagram to retrieve information from Flowchart MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data about a flowchart's structure and layout without creating, modifying, deleting, or executing anything. It is a simple observation/query operation, placing it squarely in the Read category with low severity since misuse poses minimal risk—an agent can only view diagram state, not alter it.
From the tool's definition Tool name is 'get_diagram' and description explicitly states it 'Read[s] the current state of the diagram (nodes, edges, positions)' and is used to 'observe changes the user made in the editor.' These are purely read/query operations with no side effects.
Attacks that exploit this kind of access
Read the current state of the diagram (nodes, edges, positions). Use this to observe changes the user made in the editor. It is categorised as a Read tool in the Flowchart MCP MCP Server, which means it retrieves data without modifying state.
Register the Flowchart MCP server in PolicyLayer and add a rule for get_diagram: 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 Flowchart MCP. Nothing to install.
get_diagram 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 get_diagram 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 get_diagram. 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.
get_diagram is provided by the Flowchart MCP server (zafer-liu/flowchart_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 →