AI agents invoke notes_job_wait to trigger actions in Macnotes. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool monitors and blocks on execution of a background job queue that performs write operations (as evidenced by sibling tools like notes_create, notes_delete, notes_move, and the server's support for 'background queued writes'). Calling this tool can indirectly affect when and whether queued mutations are fully committed.
From the tool's definition Tool waits for completion of a 'queued write job' — this is synchronous blocking on an asynchronous operation.
Attacks that exploit this kind of access
Wait for a queued write job to complete. It is categorised as a Execute tool in the Macnotes MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Macnotes MCP server in PolicyLayer and add a rule for notes_job_wait: 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_wait is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the notes_job_wait 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_wait. 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_wait 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.
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 →