AI agents call list_brands to retrieve information from Canva API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to list or retrieve brand data without creating, modifying, or deleting records. Despite the empty description, the naming convention and context of similar list_* and get_* siblings strongly indicate this is a read operation with no side effects. Risk is low because retrieving brand metadata poses minimal risk unless sensitive brand credentials are exposed in responses.
From the tool's definition Tool name 'list_brands' indicates a retrieval/enumeration operation. Sibling tools on this server (get_asset, get_brand, get_design, get_user, list_assets, list_designs, list_users) are all read operations that query existing data without modification.
Documented attack patterns abuse exactly the kind of access list_brands gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Canva API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_brands:
{
"version": "1",
"default": "deny",
"tools": {
"list_brands": {}
}
}list_brands is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_brands. It is categorised as a Read tool in the Canva API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Canva API MCP Server MCP server in PolicyLayer and add a rule for list_brands: 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 Canva API MCP Server. Nothing to install.
list_brands 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 list_brands 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 list_brands. 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.
list_brands is provided by the Canva API MCP Server MCP server (mattcoatsworth/canva-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Canva API MCP Server, 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.
9 Canva API MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.