Full-text search pages the user has access to (PGroonga, Korean-aware). Returns ranked hits with title and snippet.
AI agents call search_pages to retrieve information from Hubnote Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_pages retrieves and queries page data without side effects. It is a read-only search operation that returns search results. No data is created, modified, deleted, or executed. This aligns with the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).'
From the tool's definition Tool performs 'Full-text search pages the user has access to' with 'Returns ranked hits with title and snippet.' No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Full-text search pages the user has access to (PGroonga, Korean-aware). Returns ranked hits with title and snippet. It is categorised as a Read tool in the Hubnote Mcp MCP Server, which means it retrieves data without modifying state.
Register the Hubnote MCP server in PolicyLayer and add a rule for search_pages: 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 Hubnote Mcp. Nothing to install.
search_pages 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_pages 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_pages. 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_pages is provided by the Hubnote MCP server (wlzerd/hubnote-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 →