query_container · Azure Cosmos DB MCP Server MCP

WHAT IT DOES

What query_container does on Azure Cosmos DB MCP Server

AI agents invoke query_container to trigger actions in Azure Cosmos DB MCP Server. 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_container needs a policy

This tool executes SQL-like queries against an Azure Cosmos DB container. While 'query' implies read-only, SQL-like syntax can include data-modifying or destructive statements (DELETE, DROP) depending on what the API permits. Since Cosmos DB's SQL API is generally read-only for queries but the description says 'SQL-like syntax' without restricting to SELECT, this warrants Execute classification.

From the tool's definition 'Queries a Azure Cosmos DB container using SQL-like syntax' — arbitrary SQL-like syntax execution against a database container

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_container Rate-limited

query_container 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_container": {
      "limits": [
        {
          "counter": "query_container_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 Azure Cosmos DB MCP Server, so you can run agents against it safely.

FAQ

Questions about query_container

What does the query_container tool do? +

Queries a Azure Cosmos DB container using SQL-like syntax. It is categorised as a Execute tool in the Azure Cosmos DB MCP Server 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_container? +

Register the Azure Cosmos DB MCP Server MCP server in PolicyLayer and add a rule for query_container: 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 Azure Cosmos DB MCP Server. Nothing to install.

What risk level is query_container? +

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

Can I rate-limit query_container? +

Yes. Add a rate_limit block to the query_container 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_container completely? +

Set action: deny in the PolicyLayer policy for query_container. 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_container? +

query_container is provided by the Azure Cosmos DB MCP Server MCP server (robinong79/mcp-cosmos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.