jupyter_get_guidance
AI agents call jupyter_get_guidance to retrieve information from ML Jupyter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name implies querying or retrieving guidance information without modification. Given the empty description, there is inherent uncertainty, but 'get_' operations typically retrieve data without side effects. Among sibling tools that clearly execute code (execute_code, jupyter_execute_cell), this appears distinct.
From the tool's definition Tool name 'jupyter_get_guidance' suggests retrieval of guidance or documentation information. The empty description prevents definitive classification, but the 'get_' prefix indicates a read operation.
Attacks that exploit this kind of access
jupyter_get_guidance. It is categorised as a Read tool in the ML Jupyter MCP MCP Server, which means it retrieves data without modifying state.
Register the ML Jupyter MCP server in PolicyLayer and add a rule for jupyter_get_guidance: 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 ML Jupyter MCP. Nothing to install.
jupyter_get_guidance 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 jupyter_get_guidance 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 jupyter_get_guidance. 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.
jupyter_get_guidance is provided by the ML Jupyter MCP server (mayank-ketkar-sf/claudejupy). 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 →