AI agents use block_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.
An AI agent can call block_host faster than any human can review — one bad instruction and it creates or modifies resources in Defined by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Block a host, preventing it from communicating on the network. 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 block_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.
block_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 block_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 block_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.
block_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 →