AI agents use token.provision to create or update resources in Ngsrv — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ngsrv environment.
This tool creates/provisions a new authentication token, which is a Write operation (creating a credential). It does not delete or overwrite existing data, and is reversible in the sense that the token expires after 12 hours. However, misuse could allow unauthorized tunnel creation, giving it medium severity — a provisioned token grants access to start/stop tunnels and expose local services publicly.
From the tool's definition Obtain a 12-hour ngsrv agent token for tunnel commands
Attacks that exploit this kind of access
Obtain a 12-hour ngsrv agent token for tunnel commands. It is categorised as a Write tool in the Ngsrv MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ngsrv MCP server in PolicyLayer and add a rule for token.provision: 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 Ngsrv. Nothing to install.
token.provision 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 token.provision 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 token.provision. 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.
token.provision is provided by the Ngsrv MCP server (ngsrv/ngsrv-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 →