AI agents use set_configure to create or update resources in Scouter — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scouter environment.
This tool creates or modifies data reversibly by updating configuration settings. While not destructive (changes can typically be reverted), it goes beyond read-only queries. The high severity reflects that misconfigured APM servers or agents could degrade monitoring visibility, trigger false alerts, or impact application performance tracking across the entire monitored system.
From the tool's definition 'Save server or agent configuration' indicates the tool modifies configuration settings. The description explicitly states it saves/persists configuration changes to server or agent targets.
Attacks that exploit this kind of access
[HTTP mode only] Save server or agent configuration. Supports four targets:. It is categorised as a Write tool in the Scouter MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scouter MCP server in PolicyLayer and add a rule for set_configure: 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 Scouter. Nothing to install.
set_configure is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_configure 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 set_configure. 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.
set_configure is provided by the Scouter MCP server (scouter-mcp-server). 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 →