AI agents call list_notebooks to retrieve information from Marimo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of running notebooks and returns metadata (paths, ports). It performs no modifications, deletions, code execution, or external operations. It is purely informational and read-only, matching the 'Read' category definition of retrieval with no side effects. Severity is low because the information disclosed (notebook metadata) poses minimal direct risk even if misused.
From the tool's definition Tool name 'list_notebooks' and description 'List all running marimo notebooks with their paths and ports' clearly indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all running marimo notebooks with their paths and ports. It is categorised as a Read tool in the Marimo MCP Server, which means it retrieves data without modifying state.
Register the Marimo MCP server in PolicyLayer and add a rule for list_notebooks: 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 Marimo. Nothing to install.
list_notebooks 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 list_notebooks 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 list_notebooks. 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.
list_notebooks is provided by the Marimo MCP server (vladisluv12/marimo-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 →