Return embedded Dynatrace DQL (Grail) authoring knowledge so you can WRITE DQL yourself
AI agents call dql_reference to retrieve information from Dynatrace SaaS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches and returns static knowledge/documentation about DQL syntax. It has no side effects, does not execute queries, and does not modify any data. It is purely a read/reference retrieval operation. The word 'WRITE' in the description refers to the user writing DQL queries, not the tool writing data.
From the tool's definition 'Return embedded Dynatrace DQL (Grail) authoring knowledge so you can WRITE DQL yourself' — the tool returns/retrieves embedded reference documentation
Attacks that exploit this kind of access
Return embedded Dynatrace DQL (Grail) authoring knowledge so you can WRITE DQL yourself. It is categorised as a Read tool in the Dynatrace SaaS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dynatrace SaaS MCP Server MCP server in PolicyLayer and add a rule for dql_reference: 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.
dql_reference is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dql_reference 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.
Set action: deny in the PolicyLayer policy for dql_reference. 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.
dql_reference 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →