AI agents use update_host to create or update resources in Defined — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Defined environment.
The tool name 'update_host' clearly indicates modification of host records/configuration. Given the server's purpose (network administration) and the presence of related tools that create/block hosts, this is a Write operation—it modifies network infrastructure state reversibly. Severity is high because misuse could alter firewall rules, network routing, or host configurations affecting multiple network endpoints.
From the tool's definition Tool name is 'update_host' with empty description. In context of 'managing Defined Networking infrastructure' and sibling tools like 'create_host', 'block_host', 'add_firewall_rule', this tool creates or modifies host configuration reversibly.
Attacks that exploit this kind of access
update_host. It is categorised as a Write tool in the Defined MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Defined MCP server in PolicyLayer and add a rule for update_host: 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 Defined. Nothing to install.
update_host 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_host 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_host. 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_host is provided by the Defined MCP server (quickvm/defined-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 →