Quick preview of the first N rows of a resource (fetched remotely).
AI agents call preview_data to retrieve information from Ontario Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
preview_data retrieves data for inspection purposes only. It has no side effects, cannot modify or delete data, and does not execute code or trigger external operations. The limited scope (first N rows) and read-only nature makes this low-severity even if misused by an agent.
From the tool's definition Tool fetches and displays 'first N rows of a resource (fetched remotely)' with no modification, deletion, or execution capability. This is a straightforward data retrieval operation.
Attacks that exploit this kind of access
Quick preview of the first N rows of a resource (fetched remotely). It is categorised as a Read tool in the Ontario Data MCP Server, which means it retrieves data without modifying state.
Register the Ontario Data MCP server in PolicyLayer and add a rule for preview_data: 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.
preview_data 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 preview_data 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 preview_data. 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.
preview_data 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 →