Seif-Sameh/Kaggle-mcp (Seif-Sameh/Kaggle-mcp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 39 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
56/100

Seif-Sameh/Kaggle-mcp

A Model Context Protocol (MCP) server that provides seamless integration with the Kaggle API, enabling interaction with competitions, datasets, kernels, and models through MCP-compatible clients.

→ Seif-Sameh/Kaggle-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. 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 pushwhy connect →

Who stands behind it

Seif-Sameh

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
2 tools describe read intent but their handlers mutate — model_get (line 1478: with open(file_path, "w", encoding="utf-8") as f:); model_instance_get (line 1743: with open(file_path, "w", encoding="utf-8") as f:)
✅
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.
🔐
You'll be asked for 1 credential: KAGGLE_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes39 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.

competitions_list

List Kaggle competitions with optional filtering.

competition_list_files

List files available in a Kaggle competition.

competition_download_file

Download a specific file from a Kaggle competition.

competition_download_files

Download all files from a Kaggle competition.

competition_submit

Submit a file to a Kaggle competition.

competition_submissions

Get a list of all the submissions for a particular competition.

competition_leaderboard_view

Retrieve the current leaderboard for a Kaggle competition.

competition_leaderboard_download

Download the leaderboard data for a Kaggle competition to a local file.

datasets_list

Return a list of datasets.

dataset_metadata

Download the metadata file for a dataset.

dataset_list_files

Retrieve a list of all files contained within a specific Kaggle dataset.

dataset_status

Get the status of a dataset. Only for your own datasets.

dataset_download_file

Download a specific file from a Kaggle dataset to a local directory.

dataset_download_files

Download all files from a Kaggle dataset to a local directory.

dataset_create

Create a new Kaggle dataset from a local folder with metadata configuration.

dataset_initialize

Initialize a new Kaggle dataset in a local folder with metadata configuration.

dataset_create_version

Create a new version of an existing Kaggle dataset.

kernels_list

Search and list Kaggle kernels based on specified criteria.

kernel_list_files

List files associated with a specific Kaggle kernel.

kernel_initialize

Initialize kernel metadata configuration in a specified folder.

kernel_push

Push a Kaggle kernel and its metadata from a local folder.

kernel_pull

Download a Kaggle kernel and its files to a local directory.

kernel_output

Download the execution output files from a Kaggle kernel.

kernel_status

Get the status of a Kaggle kernel.

models_list

Search and list Kaggle models based on specified criteria.

model_get

Retrieve metadata and details for a specific Kaggle model, and save it as a JSON file.

model_initialize

Initialize model metadata configuration in a specified folder.

model_create

Create a new model on Kaggle using metadata from a local folder.

model_update

Update an existing model on Kaggle using metadata from a local folder.

model_delete

Delete a model from Kaggle.

model_instance_get

Retrieve details of a specific model instance from Kaggle and save as JSON.

model_instance_initialize

Initialize model instance metadata configuration in a specified folder.

model_instance_create

Create a new model instance on Kaggle using metadata from a local folder.

model_instance_update

Update an existing model instance using metadata from a local folder.

model_instance_delete

Delete a model instance from Kaggle.

model_instance_version_create

Create a new version of an existing model instance.

model_instance_version_download

Download all files for a model instance version to a local directory.

model_instance_version_files

List all files contained in a specific model instance version.

model_instance_version_delete

Delete a specific version of a model instance from Kaggle.

// 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_USERNAMEexport =your_username
🔐 secretKAGGLE_API_KEYexport =your_api_key
// 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

39/39 tools missing one or more hints — competitions_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); competition_list_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); competition_download_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +36 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.

Descriptions match behaviour

2 tools describe read intent but their handlers mutate — model_get (line 1478: with open(file_path, "w", encoding="utf-8") as f:); model_instance_get (line 1743: with open(file_path, "w", encoding="utf-8") as f:)

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

Tool inputs are validated

38/39 tool handlers declare input schemas (97%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tests exist

No test files found

Add tests that exercise each declared tool.

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 5 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/seif-sameh/kaggle-mcp?variant=verified)](https://m8ven.ai/mcp/seif-sameh/kaggle-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 62b5cb0298570dcb76fd84c0fa507d6cc529167b
code hash: db6fce1dd80bb61dc23613017c5cf76d415b90f5121c43d77848da2f1d4a1064
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