AI agents call notes_job_status to retrieve information from Macnotes 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 background job—a read-only operation that retrieves information about a queued write operation without modifying any notes, triggering execution, or causing side effects. The blast radius of misuse is minimal since it only exposes job status metadata.
From the tool's definition Tool name 'notes_job_status' and description 'Get status for a queued write job' indicate retrieval of job state information with no modification of data or execution of operations.
Attacks that exploit this kind of access
Get status for a queued write job. It is categorised as a Read tool in the Macnotes MCP Server, which means it retrieves data without modifying state.
Register the Macnotes MCP server in PolicyLayer and add a rule for notes_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 Macnotes. Nothing to install.
notes_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 notes_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 notes_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.
notes_job_status is provided by the Macnotes MCP server (zorrobyte/macnotes-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
notes_job_status is one line of Macnotes's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →