AI agents call notebook_read to retrieve information from Pernosco without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves saved notebook annotations from a debugging session without side effects. It is a read-only query operation that fits squarely in the Read category. The severity is low because notebook annotations are typically metadata or notes about a debugging session, not sensitive data that could cause harm if disclosed, and there is no capability to modify, execute, or delete anything.
From the tool's definition Tool name and description indicate it 'Read[s] Pernosco notebook annotations saved in this session' — a pure data retrieval operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Read Pernosco notebook annotations saved in this session. It is categorised as a Read tool in the Pernosco MCP Server, which means it retrieves data without modifying state.
Register the Pernosco 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 Pernosco. 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 Pernosco MCP server (jnjaeschke/pernosco-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 →