Create a note in your organization.
AI agents use note_create to create or update resources in MCP Object-Authz Lab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Object-Authz Lab environment.
This tool creates new data (notes) reversibly, fitting the Write category. Severity is medium because while note creation is not destructive, the server's documented focus on authorization vulnerabilities suggests a realistic risk that an AI agent could be tricked into creating notes in unauthorized organizational contexts or for unintended tenants.
From the tool's definition Tool name 'note_create' and description 'Create a note in your organization' explicitly indicate creation of new data.
Attacks that exploit this kind of access
Create a note in your organization. It is categorised as a Write tool in the MCP Object-Authz Lab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Object-Authz Lab MCP server in PolicyLayer and add a rule for note_create: 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 MCP Object-Authz Lab. Nothing to install.
note_create 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 note_create 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 note_create. 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.
note_create is provided by the MCP Object-Authz Lab MCP server (wrg-11/mcp-objauthz-lab). 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 →