download_resource
AI agents use download_resource to create or update resources in Ontario Data — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ontario Data environment.
The tool name suggests downloading a resource from an external portal and storing it locally (cache), which is a Write operation (creates local data). It could also be a Read if it merely fetches without persisting, but in context of a caching MCP server, download likely implies local storage. Confidence is low due to empty description.
From the tool's definition Tool name 'download_resource' on a server described as supporting 'downloading datasets from Ontario's open data portals'. Description is empty/uninformative.
Attacks that exploit this kind of access
download_resource. It is categorised as a Write tool in the Ontario Data MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ontario Data MCP server in PolicyLayer and add a rule for download_resource: 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 Ontario Data. Nothing to install.
download_resource 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 download_resource 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 download_resource. 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.
download_resource is provided by the Ontario Data MCP server (sprine/ontario-data-mcp). 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 →