AI agents use set_bios_setting to create or update resources in Cimc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cimc environment.
This tool modifies BIOS settings, which are system configuration parameters that can be changed and reverted (Write category). It is not immediately destructive since changes require a server reboot to take effect and can be undone by setting different values.
From the tool's definition Tool name 'set_bios_setting' and description states 'Modify a BIOS token value', which is a reversible configuration change that requires explicit reboot.
Attacks that exploit this kind of access
Modify a BIOS token value. Use get_bios_settings first to discover available tokens, class names, and attribute names. Requires server reboot to take effect. It is categorised as a Write tool in the Cimc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cimc MCP server in PolicyLayer and add a rule for set_bios_setting: 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 Cimc. Nothing to install.
set_bios_setting 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_bios_setting 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_bios_setting. 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_bios_setting is provided by the Cimc MCP server (schwarztim/cimc-mcp). 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 →