AI agents use update_element to create or update resources in Excalidraw — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Excalidraw environment.
The tool modifies existing elements on a canvas in a reversible manner. While the description is empty, the name and server context clearly indicate data mutation without deletion. Severity is medium because unintended modifications to diagrams could disrupt collaborative work or destroy manual layout effort, but changes are typically undoable via standard canvas undo mechanisms.
From the tool's definition Tool name 'update_element' indicates modification of existing diagram elements. The server description states it 'manipulate[s] live visual diagrams', and sibling tools include create_element, delete_element, and batch operations, establishing that this…
Documented attack patterns abuse exactly the kind of access update_element gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Excalidraw, and nothing reaches the server without passing your rules. This is the rule we recommend for update_element:
{
"version": "1",
"default": "deny",
"tools": {
"update_element": {
"limits": [
{
"counter": "update_element_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_element stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
update_element. It is categorised as a Write tool in the Excalidraw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Excalidraw MCP server in PolicyLayer and add a rule for update_element: 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 Excalidraw. Nothing to install.
update_element 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 update_element 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 update_element. 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.
update_element is provided by the Excalidraw MCP server (lesleslie/excalidraw-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Excalidraw, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Excalidraw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.