Configure system
AI agents use system-config to create or update resources in NestJS MCP Server Module — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NestJS MCP Server Module environment.
Configuring a system typically involves writing/modifying configuration state. This is reversible in principle (you can reconfigure), so Write is the appropriate category rather than Destructive. However, system-level configuration changes can have wide blast radius if misused — affecting application behavior, security settings, or service availability — hence high severity.
From the tool's definition 'Configure system' — implies modifying system-level settings or configuration
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Configure system. It is categorised as a Write tool in the NestJS MCP Server Module MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NestJS MCP Server Module MCP server in PolicyLayer and add a rule for system-config: 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 NestJS MCP Server Module. Nothing to install.
system-config 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 system-config 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 system-config. 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.
system-config is provided by the NestJS MCP Server Module MCP server (rekog-labs/mcp-nest). 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 →