// SCAN REPORT

AWS Notebook Runner MCP

13 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

3 can modify or destroy data

10 read-only

13 tools total

Community server · catalogue entry verified 02/07/2026

How to control AWS Notebook Runner MCP ↓

TOOL MAP

What AWS Notebook Runner MCP exposes to your agents

Read (10) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous AWS Notebook Runner MCP tools

Execute · High start_ec2_smoke_run This tool executes code (Jupyter notebooks) on remote cloud infrastructure, which is inherently Execute-category behavior. Execute · High start_ec2_smoke_run_async This tool executes arbitrary notebook code on AWS EC2 instances, which is a form of Execute: it runs code whose effects depend on notebook contents and incurs financial costs (marked 'paid'). Execute · High start_sagemaker_notebook_job Although financial cost is a consequence, the primary action is launching code execution on AWS SageMaker, which is an Execute operation.

3 of AWS Notebook Runner MCP's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AWS Notebook Runner MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Notebook Runner MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "check_ec2_setup": {
    "limits": [
      {
        "counter": "check_ec2_setup_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register AWS Notebook Runner MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AWS NOTEBOOK RUNNER →

Instant setup, no code required.

FULL CATALOGUE

All 13 AWS Notebook Runner MCP tools

EXECUTE 3 tools

Execute start_ec2_smoke_run Start a guarded paid EC2+SSM smoke run and terminate the instance after completion. Execute start_ec2_smoke_run_async Start a guarded paid EC2+SSM smoke run and return immediately with run ids. Execute start_sagemaker_notebook_job Start paid SageMaker notebook execution only when policy and token allow it.

READ 10 tools

Read check_ec2_setup Read-only EC2/SSM setup checks; does not launch instances. Read estimate_notebook_job_cost Estimate SageMaker notebook job compute cost from static or configured prices. Read explain_existing_aws_options Explain related AWS/AWS Labs tools and how this prototype differs. Read get_ec2_smoke_run_status Return EC2/SSM/S3 progress, CloudWatch metrics, and current cost estimate. Read get_runner_status Return local policy and dependency status without contacting AWS. Read get_sagemaker_job_status Read SageMaker pipeline execution status for a started notebook job. Read get_sagemaker_notebook_job_spec Return the SageMaker NotebookJobStep spec for a dry-run plan. Read inspect_notebook Inspect a local notebook under AWS_NOTEBOOK_RUNNER_ROOT. Read plan_ec2_smoke_run Build a dry-run EC2+SSM notebook smoke-run plan; does not launch EC2. Read plan_notebook_job Build a dry-run SageMaker notebook job plan; does not start AWS compute.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about AWS Notebook Runner MCP

Is the AWS Notebook Runner MCP server safe to use without restrictions? +

The AWS Notebook Runner MCP server is primarily read-only with 10 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the AWS Notebook Runner MCP server expose? +

13 tools across 3 categories: Execute, Read, Write. 10 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on AWS Notebook Runner MCP? +

Register the AWS Notebook Runner MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every AWS Notebook Runner MCP tool call.

Deterministic rules across all 13 AWS Notebook Runner MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AWS NOTEBOOK RUNNER →

Instant setup, no code required.

13 AWS Notebook Runner MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.