AI agents use issue_preview_token to create or update resources in Kiln — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kiln environment.
Token issuance is a write operation that creates new authentication credentials. In a 3D printer control context, preview tokens likely grant temporary access to printer resources or features. While not destructive or financial, misuse could allow an agent to create tokens for unauthorized access or escalate privileges, justifying medium severity.
From the tool's definition Tool name 'issue_preview_token' suggests creation or generation of an authentication/authorization token. The empty description limits precision, but 'issue' typically means to create or generate (e.g., 'issue a certificate', 'issue a token').
Attacks that exploit this kind of access
issue_preview_token. It is categorised as a Write tool in the Kiln MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kiln MCP server in PolicyLayer and add a rule for issue_preview_token: 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 Kiln. Nothing to install.
issue_preview_token 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 issue_preview_token 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 issue_preview_token. 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.
issue_preview_token is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →