List the notes in your organization.
AI agents call note_list to retrieve information from MCP Object-Authz Lab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries note data without side effects, making it a Read operation. However, severity is elevated to medium because: (1) this is a multi-tenant system with object-level authorization bugs (BOLA/IDOR), meaning the tool may return notes from other users/tenants if authorization is flawed; (2) in a vulnerable-by-design lab environment, misuse could expose sensitive organizational data.
From the tool's definition Tool name is 'note_list' and description states 'List the notes in your organization' — a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
List the notes in your organization. It is categorised as a Read tool in the MCP Object-Authz Lab MCP Server, which means it retrieves data without modifying state.
Register the MCP Object-Authz Lab MCP server in PolicyLayer and add a rule for note_list: 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_list 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 note_list 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_list. 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_list 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 →