Get the current working directory for notebook operations.
AI agents call get_notebook_directory to retrieve information from JupyterMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries state (the current working directory) without modifying, executing, or deleting anything. It is a simple read operation that returns information for informational purposes only. Low severity because knowing a directory path poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'get_notebook_directory' and description 'Get the current working directory' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the current working directory for notebook operations. It is categorised as a Read tool in the JupyterMCP MCP Server, which means it retrieves data without modifying state.
Register the Jupyter MCP server in PolicyLayer and add a rule for get_notebook_directory: 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 JupyterMCP. Nothing to install.
get_notebook_directory 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 get_notebook_directory 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 get_notebook_directory. 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.
get_notebook_directory is provided by the Jupyter MCP server (try3d/jupytermcp). 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 →