A
licenseB
qualityD
maintenanceLocal-first MCP server for controlling Google Colab as a development, shell, file, and training runtime, with tools for notebook editing, GPU acceleration, and file transfer.
59
7
Apache 2.0
AiAuN
by NamDT-146
Provides integration with GitHub for managing code, versioning, and code-related workflows.
Provides integration with Google Drive for storing and managing small artifacts.
Provides integration with Kaggle for accessing datasets and GPU resources to run training experiments.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AiAuNRun an ML experiment on Kaggle with the latest code and track it in W&B"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AiAuN
Local-light MCP orchestrator: GitHub for code, Kaggle for data + GPU, W&B for runs, Google Drive for small artifacts. The laptop only wraps APIs; training happens on Kaggle.
Docs
Doc | What |
Product intent | |
Keys, WSL install ( | |
Prompts, tools, features | |
Architecture and API flow | |
Package layout and how to extend |
Related MCP server: mcp-server-kaggle-exec
Quick start
Fill
.envfrom.env.example(see Setup).WSL:
bash scripts/install_wsl.sh(needs Python ≥3.10 + officialmcp; triesssemithenbasethenuv/ condaaiaun).Copy
.cursor/mcp.json.exampleto.cursor/mcp.jsonand enable theaiaunserver in Cursor.Ask the agent to run an experiment; it should ask for data dir, code version, and config if those are missing.
Phase-1 smoke uses fixtures/synthetic_color_cls (tiny PPMs), not COCO re-upload.
Maintenance
–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables running GPU-accelerated Python code on Kaggle from any MCP-compatible AI assistant without local GPU hardware.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to autonomously manage Google Colab GPU sessions, submit and monitor training jobs, and debug/fix issues via an encrypted tunnel without requiring a browser tab.MIT
- AlicenseNot gradedqualityBmaintenanceEnables ML researchers to manage experiments across local and remote AutoDL GPU instances, including experiment creation, training launch, run polling, and report writing via Claude Code.1MIT
Related MCP Connectors
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Git-backed platform for skills, tools, and context for AI agents
Autonomous dev team steered from chat: plain-English requests in, tested merged PRs out.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/NamDT-146/ML-Experiments-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server