AI agents use mermaid_to_excalidraw to create or update resources in Arch7 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arch7 environment.
The tool converts Mermaid diagrams to Excalidraw format, which creates or transforms diagram data (a Write operation). It does not execute arbitrary code or delete data. The conversion process modifies/creates diagram structures but is reversible. Low severity because misuse would only result in unwanted diagram creation/format changes with no external side effects or data loss.
From the tool's definition Tool name 'mermaid_to_excalidraw' indicates conversion/transformation of Mermaid syntax into Excalidraw diagram format. Server description indicates tools for 'creating, modifying, and converting diagrams.' Description is empty, reducing confidence.
Attacks that exploit this kind of access
mermaid_to_excalidraw. It is categorised as a Write tool in the Arch7 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arch7 MCP server in PolicyLayer and add a rule for mermaid_to_excalidraw: 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 Arch7. Nothing to install.
mermaid_to_excalidraw 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 mermaid_to_excalidraw 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 mermaid_to_excalidraw. 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.
mermaid_to_excalidraw is provided by the Arch7 MCP server (ktcrisis/arch7). 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 →