Remove a host from a group (disassociate, not delete the host).
AI agents use aap_remove_host_from_group to create or update resources in AAP MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AAP MCP Server environment.
The tool disassociates a host from a group but explicitly does not delete the host. This is a reversible modification of a relationship/membership, making it a Write operation. The host itself remains intact, so it is not Destructive. Medium severity because misconfiguration could affect automation targeting but is recoverable.
From the tool's definition Remove a host from a group (disassociate, not delete the host)
Attacks that exploit this kind of access
Remove a host from a group (disassociate, not delete the host). It is categorised as a Write tool in the AAP MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AAP MCP Server MCP server in PolicyLayer and add a rule for aap_remove_host_from_group: 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 AAP MCP Server. Nothing to install.
aap_remove_host_from_group 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 aap_remove_host_from_group 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 aap_remove_host_from_group. 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.
aap_remove_host_from_group is provided by the AAP MCP Server MCP server (srinivassrinu842/aap-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 →