query_montreal_data · Données Québec MCP: Risk & Policy

WHAT IT DOES

What query_montreal_data does on Données Québec MCP

AI agents invoke query_montreal_data 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.

WHY IT NEEDS A POLICY

Why query_montreal_data needs a policy

The server description explicitly mentions SQL queries as a capability, and sibling tools like 'find_and_query' suggest query tools on this server may execute SQL. With an empty description, there's uncertainty, but the pattern of sibling tools and server context suggests this tool likely executes queries against Montréal data sources. Confidence is reduced due to the empty description.

From the tool's definition Tool name 'query_montreal_data' and server context mentions SQL queries and spatial operations; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_montreal_data Rate-limited

query_montreal_data stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_montreal_data": {
      "limits": [
        {
          "counter": "query_montreal_data_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Données Québec MCP, so you can run agents against it safely.

FAQ

Questions about query_montreal_data

What does the query_montreal_data tool do? +

query_montreal_data. 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.

How do I enforce a policy on query_montreal_data? +

Register the Données Québec MCP server in PolicyLayer and add a rule for query_montreal_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 Données Québec MCP. Nothing to install.

What risk level is query_montreal_data? +

query_montreal_data is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_montreal_data? +

Yes. Add a rate_limit block to the query_montreal_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.

How do I block query_montreal_data completely? +

Set action: deny in the PolicyLayer policy for query_montreal_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.

What MCP server provides query_montreal_data? +

query_montreal_data 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.