Schema | AiAuN

AiAuN

Describes the environment variables required to run the server.

Name	Required	Description	Default
No arguments

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.

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`	{}

Functions exposed to the LLM to take actions

Name	Description
resolve_experiment_requestB	Check required experiment fields. If missing is non-empty, ask the user; do not run other tools yet.
inspect_local_dirA	Inspect a local data directory: file count, total bytes, sample names.
list_repo_configsA	List experiment YAML configs under semi-mask2former/configs.
kaggle_dataset_checkA	Check whether a Kaggle dataset owner/slug already exists.
kaggle_dataset_pushC	Upload a local folder as a Kaggle dataset. Size is limited only by the Kaggle API.
kaggle_kernel_pushC	Push a Kaggle script kernel. dataset_slugs is a comma-separated owner/slug list.
kaggle_kernel_statusC	Poll Kaggle kernel execution status.
kaggle_kernel_logsB	Fetch kernel output logs (often only after complete).
aiaun_smoke_scriptA	Return the inlined synthetic color-class smoke kernel source (no secrets).
aiaun_resnet50_gpu_smoke_scriptC	ResNet50 GPU smoke: short train, inference on best.pt, Drive upload of artifacts (no secrets in source). Push with enable_gpu=true.
experiment_tracking_linksC	Return Kaggle / W&B / Drive URLs the user can open to track this experiment. Always show these links in the chat.
drive_folder_infoB	Verify Google Drive service-account access to GOOGLE_DRIVE_FOLDER_ID.
drive_upload_fileB	Upload a file to the configured Drive folder (Shared Drive + SA; no browser).
kaggle_kernel_output_to_driveA	Download Kaggle kernel Output then upload to Drive via the local service account (SSH-safe, no browser). Prefer kernel-side User Secrets upload when possible.

Interactive templates invoked by user choice

Name	Description
`run_kaggle_experiment`	Workflow for running an experiment on Kaggle via this MCP.
`generate_experiment_notebook`	Guide for writing a Kaggle script that clones GitHub and uses User Secrets.

Contextual data attached and managed by the client

Name	Description
No resources

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