AWS Notebook Runner MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | Yes | AWS region, e.g., eu-north-1. | |
| AWS_PROFILE | Yes | AWS CLI profile to use. | |
| AWS_NOTEBOOK_BACKEND | Yes | Execution backend, e.g., ec2_ssm. | |
| AWS_NOTEBOOK_S3_ROOT | Yes | S3 bucket/prefix for notebook artifacts, e.g., s3://YOUR_BUCKET/runs. | |
| AWS_NOTEBOOK_ROLE_ARN | Yes | ARN of the EC2 instance role. | |
| AWS_NOTEBOOK_RUNNER_ROOT | Yes | Absolute path to local notebook directory. | |
| AWS_NOTEBOOK_MAX_RUNTIME_SECONDS | Yes | Maximum runtime in seconds. | |
| AWS_NOTEBOOK_PRICE_OVERRIDES_JSON | No | JSON string with price overrides per instance type, e.g., '{"t3.micro": 0.0104}'. | |
| AWS_NOTEBOOK_DEFAULT_INSTANCE_TYPE | Yes | Default instance type, e.g., t3.micro. | |
| AWS_NOTEBOOK_ALLOWED_INSTANCE_TYPES | Yes | Comma-separated list of allowed instance types, e.g., t3.micro,t3.small. | |
| AWS_NOTEBOOK_MAX_ESTIMATED_COST_USD | Yes | Maximum estimated cost in USD. | |
| AWS_NOTEBOOK_RUNNER_ENABLE_EXECUTION | No | Set to 'true' to enable paid compute execution. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_runner_statusA | Return local policy and dependency status without contacting AWS. |
| inspect_notebookC | Inspect a local notebook under AWS_NOTEBOOK_RUNNER_ROOT. |
| plan_notebook_jobC | Build a dry-run SageMaker notebook job plan; does not start AWS compute. |
| estimate_notebook_job_costC | Estimate SageMaker notebook job compute cost from static or configured prices. |
| check_ec2_setupA | Read-only EC2/SSM setup checks; does not launch instances. |
| plan_ec2_smoke_runA | Build a dry-run EC2+SSM notebook smoke-run plan; does not launch EC2. |
| start_ec2_smoke_runC | Start a guarded paid EC2+SSM smoke run and terminate the instance after completion. |
| start_ec2_smoke_run_asyncC | Start a guarded paid EC2+SSM smoke run and return immediately with run ids. |
| get_ec2_smoke_run_statusC | Return EC2/SSM/S3 progress, CloudWatch metrics, and current cost estimate. |
| get_sagemaker_notebook_job_specC | Return the SageMaker NotebookJobStep spec for a dry-run plan. |
| start_sagemaker_notebook_jobC | Start paid SageMaker notebook execution only when policy and token allow it. |
| get_sagemaker_job_statusC | Read SageMaker pipeline execution status for a started notebook job. |
| explain_existing_aws_optionsA | Explain related AWS/AWS Labs tools and how this prototype differs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Each tool targets a distinct action (plan, start, check status, inspect, estimate) for separate AWS execution paths (EC2+SSM vs SageMaker), with clear descriptions that prevent confusion even between start_ec2_smoke_run and start_ec2_smoke_run_async.
All tool names follow a verb_noun pattern in snake_case consistently, using action verbs like check, estimate, explain, get, inspect, plan, start. No mixed conventions.
13 tools cover the full workflow for two execution modes without bloat. Each tool serves a clear purpose in the lifecycle (plan, start, status, cost, setup, inspection).
The tool set covers setup checks, planning, starting (sync and async for EC2), status retrieval, cost estimation, and notebook inspection. Missing a cancel/abort tool for running jobs, but the guarded design mitigates this gap.