Full-text search across note content and metadata
AI agents call search_note to retrieve information from Notes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_note retrieves and queries data from existing notes without any side effects. It performs keyword-based search functionality analogous to find_note but across full content. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an agent could only retrieve information it may not have authorization for, which is a confidentiality concern but not operational risk.
From the tool's definition Tool is described as performing 'Full-text search across note content and metadata' with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Full-text search across note content and metadata. It is categorised as a Read tool in the Notes MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Notes MCP Server MCP server in PolicyLayer and add a rule for search_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 Notes MCP Server. Nothing to install.
search_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 search_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 search_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.
search_note is provided by the Notes MCP Server MCP server (namp10010/notes-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 →