execute_nql_query · Tensorus MCP: Risk & Policy

WHAT IT DOES

What execute_nql_query does on Tensorus MCP

AI agents invoke execute_nql_query to trigger actions in Tensorus 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 execute_nql_query needs a policy

This tool runs queries dynamically at runtime against a database backend. While read-only NQL queries would be 'Read', the tool permits arbitrary query execution and the description does not restrict it to read-only operations.

From the tool's definition Tool name 'execute_nql_query' with description 'Execute a Natural Query Language query' indicates runtime execution of arbitrary queries against a tensor database.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_nql_query Rate-limited

execute_nql_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": {
    "execute_nql_query": {
      "limits": [
        {
          "counter": "execute_nql_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 Tensorus MCP, so you can run agents against it safely.

FAQ

Questions about execute_nql_query

What does the execute_nql_query tool do? +

Execute a Natural Query Language query. It is categorised as a Execute tool in the Tensorus 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 execute_nql_query? +

Register the Tensorus MCP server in PolicyLayer and add a rule for execute_nql_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 Tensorus MCP. Nothing to install.

What risk level is execute_nql_query? +

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

Can I rate-limit execute_nql_query? +

Yes. Add a rate_limit block to the execute_nql_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 execute_nql_query completely? +

Set action: deny in the PolicyLayer policy for execute_nql_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 execute_nql_query? +

execute_nql_query is provided by the Tensorus MCP server (tensorus/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.