AI agents call add_host as a supporting operation in Unlimited workflows.
The description is empty, so the classification must rely on the tool name alone. 'add_host' in the context of an MCP server managing agents, queues, and providers likely registers a new host/machine for delegating work — a Write operation at most. However, given the sysops context, it could also involve infrastructure configuration. Confidence is low due to missing description.
From the tool's definition Tool name is 'add_host' but description is empty or uninformative.
Attacks that exploit this kind of access
add_host. It is categorised as a Other tool in the Unlimited MCP Server, which means it performs auxiliary operations.
Register the Unlimited MCP server in PolicyLayer and add a rule for add_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 Unlimited. Nothing to install.
add_host is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the add_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 add_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.
add_host is provided by the Unlimited MCP server (triumsebas/unlimited-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 →