execute_dql · Dynatrace SaaS MCP Server MCP: Risk & Policy

WHAT IT DOES

What execute_dql does on Dynatrace SaaS MCP Server

AI agents invoke execute_dql to trigger actions in Dynatrace SaaS 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 execute_dql needs a policy

While DQL is primarily a read-oriented query language for observability data, the 'execute' verb and ability to run arbitrary statements means an agent could craft queries with side effects or information exfiltration.

From the tool's definition Tool executes 'Dynatrace Query Language (DQL) statement' against Grail database. The term 'execute' combined with arbitrary query language execution indicates runtime code/query execution with effects dependent on the query content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_dql Rate-limited

execute_dql 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_dql": {
      "limits": [
        {
          "counter": "execute_dql_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 Dynatrace SaaS MCP Server, so you can run agents against it safely.

FAQ

Questions about execute_dql

What does the execute_dql tool do? +

Execute a Dynatrace Query Language (DQL) statement against Grail and return the result records. It is categorised as a Execute tool in the Dynatrace SaaS 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 execute_dql? +

Register the Dynatrace SaaS MCP Server MCP server in PolicyLayer and add a rule for execute_dql: 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 Dynatrace SaaS MCP Server. Nothing to install.

What risk level is execute_dql? +

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

Can I rate-limit execute_dql? +

Yes. Add a rate_limit block to the execute_dql 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_dql completely? +

Set action: deny in the PolicyLayer policy for execute_dql. 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_dql? +

execute_dql is provided by the Dynatrace SaaS MCP Server MCP server (mnmozi/dynatrace-mcp-saas). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.