Servidor MCP que permite a los usuarios de AF crear, inspeccionar y eliminar sus propios servidores JupyterLab por usuario en el clúster Kubernetes de la UChicago ATLAS Analysis Facility — los mismos notebooks que af-portal despliega hoy, expuestos como herramientas para LLMs.
LLM <--MCP/HTTP--> af-jupyterlab-mcp <--k8s API--> notebook namespace (Pod/Service/Secret/Ingress)
^
| Authorization: Bearer <broker-issued JWT>
|
af-mcp-platform credential brokerLa fase 1 (este repositorio, hoy) incluye seis herramientas que gestionan la cuádruple Pod/Service/Secret/Ingress de un notebook, portadas desde portal/jupyterlab.py de af-portal y sus cuatro plantillas Jinja. La fase 2 (en seguimiento, aún no construida) añade un proxy tipado al jupyter-mcp-server de Datalayer que se ejecuta dentro del propio notebook — véase maniaclab/af-mcp-platform#189.
Related MCP server: rucio-mcp
src/af_jupyterlab_mcp/
├── cli.py # argparse: `af-jupyterlab-mcp serve` (HTTP only)
├── config.py # env-driven Settings: namespace, domain, image allowlist, quotas
├── server.py # FastMCP setup, lifespan (k8s client + broker verifier), tool registration
├── auth/
│ └── broker.py # extract_bearer(), get_broker_claims() -- broker-issued JWT verification
├── k8s/
│ ├── errors.py # GuardrailError, NameConflictError, NotFoundOrNotYoursError, ...
│ ├── guardrails.py # CPU/memory/duration range + image allowlist validation
│ ├── names.py # sanitize_k8s_pod_name, name availability, name generation
│ ├── templates.py # Jinja rendering of the four ported manifests
│ ├── notebooks.py # create/get/list/delete notebook (ported portal logic)
│ ├── gpu.py # get_gpu_availability (ported portal logic)
│ └── templates/ # pod.yaml.j2, service.yaml.j2, secret.yaml.j2, ingress.yaml.j2
│ # (ported verbatim from af-portal/portal/templates/jupyterlab/)
└── tools/
└── jupyterlab.py # the six @mcp.tool() functionscreate_jupyter_server
list_jupyter_servers
get_jupyter_server
delete_jupyter_server
get_gpu_availability
list_supported_images
El propietario de cada servidor es siempre claims.unixname del JWT de broker verificado — ninguna herramienta acepta un argumento de propietario/nombre de usuario.
pixi run test # quick tests
pixi run lint # pre-commit + pylint
pixi run helm-lint # lint + smoke-render the Helm chartThis server cannot be deployed
Massed Compute MCP — GPU inventory, VM lifecycle, billing, SSH keys, and setup recipes.
GPU cloud platform — create, manage, and monitor instances, snapshots, SSH keys, and billing.
Read GPU instances, types, images, filesystems and firewall rules; launch and terminate instances.
On-demand GPU nodes for agents: create nodes, run commands, and submit jobs, billed by the minute.
