sql_query
AI agents invoke sql_query to trigger actions in Ontario Data. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name 'sql_query' strongly implies execution of arbitrary SQL statements against a DuckDB instance. Since the description is empty, confidence is reduced, but the name and server context (DuckDB analytics engine) suggest it runs SQL queries. DuckDB can execute DDL and DML statements (not just SELECT), so arbitrary SQL execution warrants Execute classification with high severity.
From the tool's definition Tool name 'sql_query' combined with server description mentioning 'querying' and 'high-performance analytics via DuckDB'
Attacks that exploit this kind of access
sql_query. It is categorised as a Execute tool in the Ontario Data MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ontario Data MCP server in PolicyLayer and add a rule for sql_query: 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.
sql_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sql_query 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 sql_query. 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.
sql_query 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 →