AI agents use update_policy to create or update resources in Intersight MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Intersight MCP Server environment.
This tool modifies existing policies (BIOS, boot, network, fabric settings, etc.) which can alter infrastructure behavior. Changes are reversible through subsequent updates, placing it in Write rather than Destructive. However, misconfigured policies could cascade across managed resources, justifying high severity. Confidence is high given the explicit 'update' action verb and policy management scope.
From the tool's definition Tool name 'update_policy' combined with description 'Update an existing policy' indicates modification of configuration data.
Documented attack patterns abuse exactly the kind of access update_policy gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Intersight MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_policy:
{
"version": "1",
"default": "deny",
"tools": {
"update_policy": {
"limits": [
{
"counter": "update_policy_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_policy stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing policy. It is categorised as a Write tool in the Intersight MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Intersight MCP Server MCP server in PolicyLayer and add a rule for update_policy: 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 Intersight MCP Server. Nothing to install.
update_policy 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 update_policy 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 update_policy. 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.
update_policy is provided by the Intersight MCP Server MCP server (jim-coyne/intersight_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Intersight MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
198 Intersight MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.