AI agents call get_asset 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 'get_asset' tool appears to retrieve asset information from Canva's API based on its name and position among other retrieval-focused sibling tools. No side effects or data modification capabilities are indicated. This is a straightforward Read operation with minimal security risk unless asset data itself is sensitive (mitigated by Canva's own access controls).
From the tool's definition Tool name is 'get_asset' which follows a standard GET/retrieval pattern. Sibling tools like 'get_brand', 'get_design', and 'get_user' are clearly Read operations.
Documented attack patterns abuse exactly the kind of access get_asset 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 get_asset:
{
"version": "1",
"default": "deny",
"tools": {
"get_asset": {}
}
}get_asset 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.
get_asset. 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 get_asset: 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.
get_asset 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_asset 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_asset. 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_asset 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.