Build a dry-run SageMaker notebook job plan; does not start AWS compute.
AI agents call plan_notebook_job to retrieve information from AWS Notebook Runner MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it is a dry-run that does not start any AWS compute. It only constructs a plan/preview, making it a read/query operation with no side effects. No resources are created, modified, or destroyed.
From the tool's definition 'Build a dry-run SageMaker notebook job plan; does not start AWS compute.'
Attacks that exploit this kind of access
Build a dry-run SageMaker notebook job plan; does not start AWS compute. It is categorised as a Read tool in the AWS Notebook Runner MCP MCP Server, which means it retrieves data without modifying state.
Register the AWS Notebook Runner MCP server in PolicyLayer and add a rule for plan_notebook_job: 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 AWS Notebook Runner MCP. Nothing to install.
plan_notebook_job 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 plan_notebook_job 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 plan_notebook_job. 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.
plan_notebook_job is provided by the AWS Notebook Runner MCP server (yummytastycode/aws-notebook-runner-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 →