query_resource_sql
AI agents invoke query_resource_sql to trigger actions in Données Québec MCP. 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 name contains 'sql' suggesting it runs SQL queries against a data resource. SQL execution can have wide-ranging effects depending on permissions — potentially reading, writing, or even destructive operations (DROP, DELETE). With an empty description, we cannot confirm read-only constraints, so we escalate to Execute. Severity is high given the blast radius of arbitrary SQL execution if misused.
From the tool's definition Tool name 'query_resource_sql' strongly implies execution of SQL queries; description is empty and provides no further detail.
Attacks that exploit this kind of access
query_resource_sql. It is categorised as a Execute tool in the Données Québec MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Données Québec MCP server in PolicyLayer and add a rule for query_resource_sql: 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 Données Québec MCP. Nothing to install.
query_resource_sql 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 query_resource_sql 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 query_resource_sql. 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.
query_resource_sql is provided by the Données Québec MCP server (stefen-taime/donneesqc-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 →