cosmosdb_item_query · Azure MCP Server MCP: Risk & Policy

WHAT IT DOES

What cosmosdb_item_query does on Azure MCP Server

AI agents invoke cosmosdb_item_query to trigger actions in Azure 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 cosmosdb_item_query needs a policy

This tool executes SQL queries against a Cosmos DB container. While typical usage may be read-only, arbitrary SQL execution can include operations with side effects or be used to extract large volumes of sensitive data. The ability to run arbitrary SQL elevates this beyond a simple Read tool. Severity is high due to potential for data exfiltration or unintended query execution at scale across a cloud database.

From the tool's definition 'Query items in a Cosmos DB container using SQL' — executes arbitrary SQL queries against Cosmos DB

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cosmosdb_item_query Rate-limited

cosmosdb_item_query 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": {
    "cosmosdb_item_query": {
      "limits": [
        {
          "counter": "cosmosdb_item_query_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about cosmosdb_item_query

What does the cosmosdb_item_query tool do? +

Query items in a Cosmos DB container using SQL. It is categorised as a Execute tool in the Azure 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 cosmosdb_item_query? +

Register the Azure MCP Server MCP server in PolicyLayer and add a rule for cosmosdb_item_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 Azure MCP Server. Nothing to install.

What risk level is cosmosdb_item_query? +

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

Can I rate-limit cosmosdb_item_query? +

Yes. Add a rate_limit block to the cosmosdb_item_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.

How do I block cosmosdb_item_query completely? +

Set action: deny in the PolicyLayer policy for cosmosdb_item_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.

What MCP server provides cosmosdb_item_query? +

cosmosdb_item_query is provided by the Azure MCP Server MCP server (mashriram/azure_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.