query_traces

Query Datadog APM traces for a service. Returns trace data with

Server MCP Datadog Server micaelmalta/mcp-server-datadog
Category Read
Risk class Low
Parameters 00 required

What query_traces does on MCP Datadog Server

AI agents call query_traces to retrieve information from MCP Datadog Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why query_traces needs a policy

This tool retrieves APM trace data from Datadog without creating, modifying, deleting, or executing operations. It is a read-only query operation. Severity is medium rather than low because APM traces may contain sensitive operational details, performance metrics, or user activity patterns that could enable reconnaissance or information disclosure if misused by an untrusted agent.

From the tool's definition Tool name 'query_traces' and description 'Query Datadog APM traces for a service. Returns trace data' indicate data retrieval without modification. The action is a query operation that fetches existing trace data.

Questions about query_traces

What does the query_traces tool do? +

Query Datadog APM traces for a service. Returns trace data with. It is categorised as a Read tool in the MCP Datadog Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on query_traces? +

Register the MCP Datadog Server MCP server in PolicyLayer and add a rule for query_traces: 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 MCP Datadog Server. Nothing to install.

What risk level is query_traces? +

query_traces is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit query_traces? +

Yes. Add a rate_limit block to the query_traces 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_traces completely? +

Set action: deny in the PolicyLayer policy for query_traces. 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_traces? +

query_traces is provided by the MCP Datadog Server MCP server (micaelmalta/mcp-server-datadog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.