AI agents call provider_job_status to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the status of an existing job managed by a remote provider. It performs no side effects, creates no data, executes no commands, and deletes nothing. It is purely informational retrieval, fitting the Read category. Severity is low because status checks pose minimal risk even if misused by an agent—they cannot alter printer state, delete files, or cause physical damage.
From the tool's definition Tool name 'provider_job_status' and description 'Check status of a provider-managed remote job' indicate a read-only query operation that retrieves status information without modifying state or triggering actions.
Attacks that exploit this kind of access
Check status of a provider-managed remote job. It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for provider_job_status: 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.
provider_job_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the provider_job_status 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 provider_job_status. 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.
provider_job_status 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 →