AI agents call read_note to retrieve information from MCP Notes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a personal knowledge management system without causing any side effects. It performs a query/fetch operation on existing notes, fitting the 'Read' category. Severity is low because even if an agent reads all notes, the operation is non-destructive and reversible; the worst outcome is information disclosure of the user's own knowledge base.
From the tool's definition Tool name is 'read_note' and description states it 'Read[s] the complete contents of a note file' — a straightforward retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Read the complete contents of a note file from your notes directory. It is categorised as a Read tool in the MCP Notes MCP Server, which means it retrieves data without modifying state.
Register the MCP Notes MCP server in PolicyLayer and add a rule for read_note: 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 Notes. Nothing to install.
read_note 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 read_note 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 read_note. 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.
read_note is provided by the MCP Notes MCP server (mikeysrecipes/mcp-notes). 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 →