af-jupyterhub-mcp
Lets users start, inspect, stop, and delete their own named JupyterHub servers on jupyterhub.af.uchicago.edu, and work inside them. Provides notebook tools to run code and edit notebooks, plus JupyterLab UI tools, reaching each server's jupyter-mcp-server through the hub proxy. Also lists supported images and sites and reports spawn progress.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
af-jupyterhub-mcp
MCP server that lets UChicago ATLAS Analysis Facility users start, inspect, stop, and delete their own JupyterHub named servers on jupyterhub.af.uchicago.edu, and work inside them (run code, edit notebooks, drive the JupyterLab UI), as tools for LLMs behind the af-mcp-platform broker.
Architecture
LLM <--MCP/HTTP--> af-mcp-platform aggregator --Bearer: linked hub token--> af-jupyterhub-mcp
|
JupyterHub REST API <------------------+
/hub/api/users/<you>/servers/<name> |
hub proxy /user/<you>/<name>/mcp <-----+--> jupyter-mcp-serverEverything goes through JupyterHub and nothing else. Servers are started with
POST /hub/api/users/<you>/servers/<name>, whose body is the spawner's
user_options (image, site, CPU, memory, QoS, GPUs). The tool then follows the
hub's spawn progress stream, sending MCP progress notifications until the server
is ready. Notebook tools reach the server's own jupyter-mcp-server through the
hub proxy, so they work for servers on any site (local, ssl, nrp). The
backend never talks to Kubernetes or BinderHub. Servers launched from the
BinderHub UI are ordinary named servers of the same user, so they show up and
work here too.
Launched images must include jupyterhub-singleuser (ml_platform has since
#21) and
jupyter-mcp-server (plus jupyter-mcp-tools for the nb_ui_* tools).
Related MCP server: Apache Zeppelin MCP Server
Authentication
The user's own hub token. af-mcp-platform links each user's JupyterHub account through the hub's OAuth (
oauth21-direct, confidential clientservice-af-mcp-platform). It forwards the linked token asAuthorization: Bearer <hub token>. The backend has no credentials of its own and uses that token for every hub and notebook call, so its trust tier isuser-tier.Identity. The caller is resolved with
GET /hub/api/user. The result is cached for 60 s, keyed by the token's SHA-256. The hub username is the owner of every server a tool touches; no tool takes an owner argument.Required scopes.
servers!user,access:servers!userandread:users:name!user. A token without them gets an error that names the missing scopes.Token lifetime. The link token uses the hub's default 14-day lifetime. The hub issues no refresh token, so users re-link when it expires; the tools then say to re-link.
Secrets stay out of results. Tokens never appear in tool results or logs. That includes the
tokenBinderHub stores in a server'suser_options.
Tools
76 tools: seven for the server lifecycle, 17 nb_* notebook tools, and 52
nb_ui_* JupyterLab UI tools. See docs/tools.md for the full
reference.
Tool | Does | Kind |
| Start a named server and wait until it is ready, with progress | mutating |
| List your named servers, stopped ones included | read-only |
| Show one server's status, image, resources, and URL | read-only |
| Stop a server but keep its entry (it still counts toward the 10) | destructive |
| Stop a server and remove its entry | destructive |
| List the CPU and GPU images | read-only |
| List the site names | read-only |
Build and test commands
pixi run test # unit + integration tests (fake hub, no network)
pixi run -e py312 test-e2e # live hub; needs AF_JUPYTERHUB_E2E_TOKEN
pixi run lint # pre-commit + pylint
pixi run helm-lint # lint + smoke-render the Helm chart
pixi run docs-serve # build and serve the docsSee docs/configuration.md and docs/deployment.md for running it.
Tool 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
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
On-demand GPU nodes for agents: create nodes, run commands, and submit jobs, billed by the minute.
Create, watch, pay for and connect hosted AI agent pods on AgentsPodium. Needs an API key.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to create, read, edit, and execute Jupyter notebook cells, manage kernels, and connect to remote Jupyter servers.2128 PyPIMIT
- AlicenseAqualityBmaintenanceEnables LLM agents to interact with Apache Zeppelin notebooks via the Zeppelin REST API, supporting operations like listing, searching, editing, and running notebooks.3312MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to create, inspect, list, and delete per-user JupyterLab servers on the UChicago ATLAS Analysis Facility Kubernetes cluster, with GPU availability and supported image listing tools.84 PyPIApache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables AI coding agents to run policy-constrained Python jobs on lab NVIDIA GPU hosts, including GPU inspection, device reservation, job launching and monitoring, and owner-scoped process stopping.2-