AI agents use upload_image to create or update resources in Canva API MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Canva API MCP Server environment.
The tool creates or adds image data to Canva's system, which is a reversible write operation. Without a description detailing whether it permits overwrites, deletion, or has destructive side effects, Write is the appropriate category. Severity is medium because misuse could fill storage or create unwanted design assets, but effects are contained within Canva and reversible.
From the tool's definition Tool name 'upload_image' indicates creation/modification of assets in Canva. Description is empty, limiting certainty. Sibling tools show this server manages designs, brands, and assets.
Documented attack patterns abuse exactly the kind of access upload_image 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 upload_image:
{
"version": "1",
"default": "deny",
"tools": {
"upload_image": {
"limits": [
{
"counter": "upload_image_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_image 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.
upload_image. It is categorised as a Write tool in the Canva API MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Canva API MCP Server MCP server in PolicyLayer and add a rule for upload_image: 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.
upload_image 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 upload_image 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 upload_image. 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.
upload_image 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.