Searches cells for a keyword, showing which cell matches were found with contextual snippets
AI agents call notebook_search to retrieve information from Claude Code Notebook MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about notebook cells matching a search query. It does not modify, create, delete, execute, or destroy any data. It is a pure information retrieval function with no side effects, placing it firmly in the Read category. The low severity reflects minimal risk even if misused by an AI agent—it can only expose existing notebook content.
From the tool's definition The tool description states it "Searches cells for a keyword, showing which cell matches were found with contextual snippets." The word 'Searches' and the fact that it returns match results with context indicates a read-only query operation with no side…
Documented attack patterns abuse exactly the kind of access notebook_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code Notebook MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for notebook_search:
{
"version": "1",
"default": "deny",
"tools": {
"notebook_search": {}
}
} notebook_search 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.
Searches cells for a keyword, showing which cell matches were found with contextual snippets. It is categorised as a Read tool in the Claude Code Notebook MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Code Notebook MCP server in PolicyLayer and add a rule for notebook_search: 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 Claude Code Notebook MCP. Nothing to install.
notebook_search 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_search 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_search. 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_search is provided by the Claude Code Notebook MCP server (mstampfer/claude-code-notebook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code Notebook MCP, 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 Claude Code Notebook MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.