AI agents call research_poll to retrieve information from Notebooklm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information and results from a research operation that was presumably initiated elsewhere. Polling is a read operation—it queries state without side effects, changes, or external actions. The low severity reflects that misuse would only expose information already generated, not trigger new operations or modify data.
From the tool's definition Tool name 'research_poll' combined with description 'Poll for research status and results' indicates querying/checking the status of an existing research operation and retrieving its results without modifying or executing new operations.
Documented attack patterns abuse exactly the kind of access research_poll gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Notebooklm, and nothing reaches the server without passing your rules. This is the rule we recommend for research_poll:
{
"version": "1",
"default": "deny",
"tools": {
"research_poll": {}
}
}research_poll is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Poll for research status and results. It is categorised as a Read tool in the Notebooklm MCP Server, which means it retrieves data without modifying state.
Register the Notebooklm MCP server in PolicyLayer and add a rule for research_poll: 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 Notebooklm. Nothing to install.
research_poll 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 research_poll 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 research_poll. 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.
research_poll is provided by the Notebooklm MCP server (moodrobotics/notebooklm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Notebooklm, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Notebooklm tools catalogued and risk-classified — across an index of 43,000+ MCP servers.