AI agents call searchNotes to retrieve information from Memnote without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
q | string | Yes | Natural language search query |
limit | integer | — | Max results (1–20, default 10) |
includeDeleted | boolean | — | Include soft-deleted notes (default false) |
Parameters from the server's own tool schema.
The tool searches and retrieves notes based on vector similarity but does not create, modify, delete, execute external code, or move money. It is a read-only query operation with minimal blast radius—worst case, it returns information the authenticated user already has access to.
From the tool's definition Tool description explicitly states it performs 'Semantic vector search across the authenticated user's notes' and 'Returns notes ranked by cosine similarity to the query.' This is a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Search notes Semantic vector search across the authenticated user's notes. Returns notes ranked by cosine similarity to the query. It is categorised as a Read tool in the Memnote MCP Server, which means it retrieves data without modifying state.
searchNotes accepts 3 parameters: q, limit, includeDeleted. Required: q. The full parameter table on this page comes from the server's own tool schema.
Register the Memnote MCP server in PolicyLayer and add a rule for searchNotes: 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 Memnote. Nothing to install.
searchNotes 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 searchNotes 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 searchNotes. 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.
searchNotes is provided by the Memnote MCP server (@randomfact/memnote-mcp-server). 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 →