kaggle-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KAGGLE_KEY | No | Kaggle API key, required if kaggle.json is not set up. | |
| KAGGLE_USERNAME | No | Kaggle username, required if kaggle.json is not set up. |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| prepare_kaggle_datasetB | Download and extract a Kaggle dataset. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools, so disambiguation is perfect.
The single tool follows a consistent verb_noun pattern (prepare_kaggle_dataset), so naming is perfectly consistent.
Only one tool for a server named 'kaggle-mcp' is far too few; a typical Kaggle interaction requires multiple operations beyond just downloading.
The single tool covers only dataset download/extraction, missing essential CRUD operations, search, and listing, making the surface severely incomplete.