Apply a color theme to the diagram.
AI agents use apply_theme to create or update resources in Flowchart MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Flowchart MCP environment.
Applying a theme creates or modifies diagram metadata (theme selection) reversibly. It does not execute code, delete data, or cause side effects beyond visual rendering. This is a low-severity write operation because theme changes are easily undone by applying a different theme and have minimal business impact.
From the tool's definition Tool 'apply_theme' modifies diagram properties (color theme) reversibly. It changes visual presentation of an existing diagram without deleting data or executing external code.
Attacks that exploit this kind of access
Apply a color theme to the diagram. It is categorised as a Write tool in the Flowchart MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Flowchart MCP server in PolicyLayer and add a rule for apply_theme: 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.
apply_theme is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the apply_theme 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 apply_theme. 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.
apply_theme 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 →