notebook_read
AI agents call notebook_read to retrieve information from MCP Claude Code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the tool name 'notebook_read' unambiguously indicates retrieval of notebook content without modification. No side effects, code execution, or data destruction implied. Confidence slightly lowered due to missing description, but naming convention is sufficiently clear. Grouped with 'read' sibling tool which reinforces the read-only nature.
From the tool's definition Tool name 'notebook_read' clearly indicates a read-only operation on notebook files. The 'read' sibling tool on the same server further confirms this pattern of read operations.
Attacks that exploit this kind of access
notebook_read. It is categorised as a Read tool in the MCP Claude Code MCP Server, which means it retrieves data without modifying state.
Register the MCP Claude Code MCP server in PolicyLayer and add a rule for notebook_read: 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 MCP Claude Code. Nothing to install.
notebook_read 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 notebook_read 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 notebook_read. 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.
notebook_read is provided by the MCP Claude Code MCP server (sdglbl/mcp-claude-code). 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 →