af-jupyterlab-mcp
af-jupyterlab-mcp
MCP-Server, der es AF-Benutzern ermöglicht, ihre eigenen JupyterLab-Server pro Benutzer auf dem Kubernetes-Cluster der UChicago ATLAS Analysis Facility zu erstellen, zu inspizieren und zu löschen – dieselben Notebooks, die af-portal heute bereitstellt, als Tools für LLMs.
Architektur
LLM <--MCP/HTTP--> af-jupyterlab-mcp <--k8s API--> notebook namespace (Pod/Service/Secret/Ingress)
^
| Authorization: Bearer <broker-issued JWT>
|
af-mcp-platform credential brokerPhase 1 (dieses Repo, heute) liefert sechs Tools, die das Pod/Service/Secret/Ingress-Quartett für ein Notebook verwalten, portiert aus af-portals portal/jupyterlab.py und seinen vier Jinja-Vorlagen. Phase 2 (verfolgt, noch nicht gebaut) ergänzt einen typisierten Proxy zum Datalayer jupyter-mcp-server, der im Notebook selbst läuft – siehe maniaclab/af-mcp-platform#189.
Related MCP server: rucio-mcp
Projektstruktur
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() functionsTool-Oberfläche
create_jupyter_serverlist_jupyter_serversget_jupyter_serverdelete_jupyter_serverget_gpu_availabilitylist_supported_images
Der Besitzer jedes Servers ist immer claims.unixname aus dem verifizierten Broker-JWT – kein Tool akzeptiert ein Besitzer-/Benutzername-Argument.
Build- und Testbefehle
pixi run test # quick tests
pixi run lint # pre-commit + pylint
pixi run helm-lint # lint + smoke-render the Helm chartTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
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.
Deploy applications and manage governed Kubernetes preview spaces and capacity.
Related MCP Servers
- FlicenseAqualityCmaintenanceAn MCP server that enables LLMs to execute Python code on GPU-accelerated compute nodes within SLURM-managed HPC environments. It bridges local clients to remote clusters by launching JupyterLab sessions via SLURM jobs to facilitate high-performance notebook-based computation.7-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that exposes Rucio distributed data management operations as tools for LLMs. Designed for ATLAS physicists working with grid data on analysis facilities, but usable with any Rucio instance.6Apache 2.0
- AlicenseAqualityDmaintenanceEnables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.6MIT
- AlicenseAqualityDmaintenanceAI-powered MCP server for connecting and managing Jupyter Notebooks. Enables interactive code execution, multi-notebook management, and multimodal output for data analysis, visualization, and machine learning.12101 PyPI9MIT