suggest_sql
AI agents invoke suggest_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 server description explicitly mentions SQL queries as a capability. A tool named 'suggest_sql' likely generates or executes SQL queries. Given the sibling tool 'find_and_query' also exists, this tool may 'suggest' SQL rather than execute it, which would be Read/Write, but could also execute the suggested SQL. With an empty description, confidence is low.
From the tool's definition Tool name 'suggest_sql' on a server that supports 'SQL queries' per server description; description is empty/uninformative.
Attacks that exploit this kind of access
suggest_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 suggest_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.
suggest_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 suggest_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 suggest_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.
suggest_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 →