AI agents call remnote_search to retrieve information from Remnote without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from a knowledge base without side effects. Searching is a read-only operation that does not create, modify, delete, or execute anything. The low severity reflects minimal risk—an AI agent misusing search has limited negative impact compared to tools that modify or delete data.
From the tool's definition Tool name 'remnote_search' and description 'Search the RemNote knowledge base' indicate querying/retrieving data. The mention of 'cursor paging through hasMore/nextCursor' and 'contentMode' options are consistent with retrieval operations.
Attacks that exploit this kind of access
Search the RemNote knowledge base. Supports cursor paging through hasMore/nextCursor. For whole-KB orientation, prefer contentMode=. It is categorised as a Read tool in the Remnote MCP Server, which means it retrieves data without modifying state.
Register the Remnote MCP server in PolicyLayer and add a rule for remnote_search: 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 Remnote. Nothing to install.
remnote_search 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 remnote_search 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 remnote_search. 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.
remnote_search is provided by the Remnote MCP server (remnote-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 →