Get the full extracted text of a source.
AI agents call source_fulltext to retrieve information from NotebookLM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (full text content of a source) without modifying, deleting, or executing anything. It is a query/fetch operation that poses minimal risk if misused by an AI agent—the worst outcome would be unauthorized access to text content already stored in NotebookLM sources.
From the tool's definition The tool name is 'source_fulltext' and the description states 'Get the full extracted text of a source.' The verb 'get' and the action of retrieving text are characteristic of read operations with no side effects.
Attacks that exploit this kind of access
Get the full extracted text of a source. It is categorised as a Read tool in the NotebookLM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NotebookLM MCP Server MCP server in PolicyLayer and add a rule for source_fulltext: 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 MCP Server. Nothing to install.
source_fulltext 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 source_fulltext 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 source_fulltext. 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.
source_fulltext is provided by the NotebookLM MCP Server MCP server (pavelguzenfeld/notebooklm-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 →