kaggle-mcp-server (tripathysagar/kaggle-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 39 out of 100, grade F. It declares 96 tools. No publisher has claimed this listing.

Warning

39/100

kaggle-mcp-server

Item: kaggle-mcp-server
Rating: 39
Author: M8ven

A full-featured MCP server with 96 tools for the Kaggle API, enabling users to manage competitions, datasets, notebooks, models, discussions, and workflows via natural language.

→ tripathysagar/kaggle-mcp-server · listed on glama

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

tripathysagar

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

⚠️

Tool descriptions don’t match what handlers do

1 tool describes read intent but its handler mutates — competition_full_setup (line 667: zf.unlink())

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

// tools this server exposes96 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

benchmark_leaderboard

Get the leaderboard for a Kaggle benchmark.

competitions_list

Search and list Kaggle competitions.

competition_files

List data files for a competition.

competition_download

Download competition data files. Returns download URL.

competition_submit

Submit predictions to a competition.

competition_submissions

View submission history for a competition.

competition_leaderboard

View competition leaderboard (top 20).

competition_get

Get detailed competition info.

competition_data_summary

Get data files summary for a competition.

competition_get_submission

Get details for a single submission.

competition_leaderboard_download

Download the full competition leaderboard. Returns download URL.

datasets_list

Search and list Kaggle datasets.

dataset_files

List files in a dataset.

dataset_download

Download dataset files. Returns download URL.

dataset_metadata

Get dataset metadata.

dataset_create

Create a new dataset. Use file_upload first to get file tokens.

file_upload

Upload a file to Kaggle and get a token for dataset_create.

dataset_get

Get full dataset info.

dataset_create_version

Create a new version of an existing dataset.

dataset_update_metadata

Update dataset metadata (title, description, license).

dataset_delete

Delete a dataset.

dataset_download_file

Download a single file from a dataset. Returns download URL.

discussions_search

Search Kaggle discussions.

discussions_list

List discussions for a competition or dataset.

discussion_detail

Get discussion content by ID.

discussion_comments

Get comments for a discussion.

discussion_comments_search

Search comments across all Kaggle discussions.

discussions_by_source

Browse discussions by source type.

discussions_solutions

Browse competition solution write-ups.

discussions_writeups

Browse Kaggle write-ups by type.

discussions_trending

Browse trending discussions sorted by hotness.

discussions_my

List the current user's discussions.

submit_local_file

Submit a local prediction file (CSV etc.) to a Kaggle competition.

submit_code_competition

Submit to a code competition (kernels-only competitions).

kernel_status

Check the execution status of a notebook/kernel.

kernel_files

List files belonging to a kernel/notebook.

kernel_delete

Delete a kernel/notebook from Kaggle.

kernel_initialize

Initialize a new kernel template in a local directory.

kernel_download_output_zip

Download all output files from a kernel as a zip.

dataset_status

Check the processing status of a dataset.

my_datasets

List your own Kaggle datasets.

datasets_by_user

List all public datasets owned by a specific user.

dataset_files_summary

Get a summary of files in a dataset (total size, file count).

model_instance_delete

Delete a model instance.

model_instance_files

List files for the current version of a model instance.

model_instance_version_download

Download files for a specific model instance version.

model_instance_version_files

List files in a specific model instance version.

model_instance_version_delete

Delete a specific model instance version.

preview_csv

Preview the first N rows of a local CSV file.

preview_data_file

Preview the first N lines of any local data file (JSON, txt, etc.).

list_local_files

List files in a local directory with sizes.

upcoming_deadlines

Show competitions with upcoming deadlines, sorted by closest deadline.

competition_full_setup

One-shot competition setup: get info, download data, list files, preview CSVs.

my_competitions

List competitions you have entered (have submissions in).

competition_download_single_file

Download a single file from a competition to a local directory.

search_everything

Unified search across competitions, datasets, and notebooks.

dataset_tree_files

Show a hierarchical tree view of files and directories in a dataset.

competition_tree_files

Show a hierarchical tree view of competition data files.

model_metrics

Get performance metrics for a Kaggle model.

track_operation

Check the status of a long-running Kaggle operation.

submission_score

Get the score of your latest (or specific) submission.

compare_csvs

Compare two CSV files and report differences.

generate_starter_notebook

Generate a starter Jupyter notebook for a Kaggle competition.

leaderboard_position

Find a specific team or user's position on a competition leaderboard.

csv_column_analysis

Analyze column types and basic statistics of a CSV file without pandas.

setup_comp

Download and extract competition data locally, returning the path.

check_dataset_exists

Check whether a Kaggle dataset exists.

download_dataset_local

Download a Kaggle dataset to a local directory and optionally unzip.

create_dataset_from_files

Create a new Kaggle dataset from a local directory.

push_dataset_version

Push an updated version of an existing dataset.

generate_notebook_metadata

Generate a kernel-metadata.json dict for pushing notebooks.

push_notebook_file

Push a local notebook file to Kaggle Notebooks.

download_pip_library

Download pip wheel files for a library (for offline Kaggle use).

download_pip_requirements

Download pip wheel files for everything in a requirements.txt.

create_library_dataset

Download a pip library and upload it as a Kaggle dataset.

create_requirements_dataset

Download all packages from requirements.txt and upload as a Kaggle dataset.

get_local_library_version

Check the version of a pip library stored in a local dataset directory.

kernels_list

Search and list Kaggle notebooks/kernels.

kernel_pull

Get a notebook's source code.

kernel_push

Push/save a notebook to Kaggle.

kernel_output

Download kernel output files. Returns download URL.

kernel_session_create

Create an interactive kernel session.

kernel_session_status

Get status of a kernel session.

kernel_session_output

List output files from a kernel session.

kernel_session_cancel

Cancel a running kernel session.

competition_top_kernels

List top public kernels/notebooks for a competition, sorted by public score.

models_list

Search and list Kaggle models.

model_get

Get detailed information about a specific model.

model_create

Create a new Kaggle model.

model_update

Update an existing Kaggle model.

model_delete

Delete a Kaggle model.

model_instances_list

List all instances of a Kaggle model.

model_instance_get

Get details of a specific model instance.

model_instance_create

Create a new instance for a Kaggle model.

model_instance_versions

List all versions of a model instance.

model_instance_version_create

Create a new version for a model instance.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configKAGGLE_USERNAME

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

96/96 tools missing one or more hints — benchmark_leaderboard (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); competitions_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); competition_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +93 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

3 tools perform destructive updates without destructiveHint — competition_full_setup deletes at line 667 (zf.unlink()); setup_comp deletes at line 96 (zip_file.unlink()); create_requirements_dataset deletes at line 482 (shutil.rmtree(f))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — competition_full_setup (line 667: zf.unlink())

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool handlers catch errors

94/96 tool handlers wrap calls in try/catch (98%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Tool description accuracy

competition_full_setup: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/tripathysagar/kaggle-mcp-server?variant=verified)](https://m8ven.ai/mcp/tripathysagar/kaggle-mcp-server)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 559eb0eda69eaddd452806a7b480673188b1b138

code hash: 4cfe0438dc950cf542aef4dd5ac5fca512bcee9e4884764fb8dd775faf42c456

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client