kaggle-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Runs local Python projects as background jobs on Kaggle's free machines.
Jobs run on Kaggle, independent of this session: submit_job returns immediately.
To be notified when a job finishes, run the shell command kjob wait <job_id> in the
background (it polls every 60s and exits when the job is done), then call job_output.
Job state is kept locally, so after a session restart list_jobs shows earlier jobs.
Runs are capped at 12 h: for longer work the script checkpoints into its cwd, and when
job_output reports incomplete, submit the same job again with resume_from=.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| submit_jobA | Run a Python project on Kaggle as a private background job; returns immediately. |
| job_statusB | Current status of a job: queued, running, complete, error or cancel_*. |
| list_jobsA | All jobs submitted from this machine, newest first. refresh=True asks Kaggle for status. |
| job_logsB | stdout/stderr of a job's latest run (last tail_chars characters; 0 = all). |
| job_outputA | Download a finished job's output files (default: <project_dir>/kaggle_out/<job_id>/). |
| cleanup_jobA | Delete a finished job's kernel (with its outputs) and per-job dataset from Kaggle. |
| upload_datasetA | Upload a local directory as a private Kaggle dataset to reuse across jobs. |
| list_datasetsB | Datasets uploaded with upload_dataset that still exist. |
| delete_datasetA | Delete a dataset created by upload_dataset. Refuses if an unfinished job uses it. |
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 9 tools
Each tool maps to a distinct action in the job or dataset lifecycle, and descriptions clarify the boundaries between look-alike pairs (job_status vs list_jobs, job_logs vs job_output). The only mild overlap is cleanup_job, which deletes a kernel plus its per-job dataset, versus delete_dataset for uploaded datasets — but the descriptions make that distinction explicit.
Eight of nine names follow a predictable snake_case verb_noun pattern (submit_job, list_jobs, upload_dataset, delete_dataset). The read-side tools (job_status, job_logs, job_output) drop the verb and lead with the noun, a minor but noticeable inconsistency in an otherwise clean scheme.
Nine tools is well scoped: six cover the remote job lifecycle and three cover reusable datasets, with no filler. Nothing looks redundant or missing from a count perspective.
The job lifecycle (submit, status, list, logs, output, cleanup) and dataset lifecycle (upload, list, delete) are both well covered. The notable gap is cancellation — job_status reports cancel_* states, yet there is no tool to cancel a running job, forcing reliance on time_limit_h.