kaggle-mcp (parkseokjune/kaggle-mcp) is an MCP server listed on the M8ven Trust Index. It scores 36 out of 100, grade F. It declares 41 tools. No publisher has claimed this listing.

F
Warning
36/100

kaggle-mcp

A safety-first MCP server that connects Claude to Kaggle, enabling competition management, dataset analysis, submission tracking, and kernel execution with built-in safeguards against destructive actions and prompt injection.

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 pushwhy connect →

Who stands behind it

parkseokjune

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 →

Install from

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 — kaggle_eda_competition (line 251: z.unlink()); kaggle_eda_dataset (line 97: z.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.
🔐
You'll be asked for 2 credentials: KAGGLE_KEY, KAGGLE_API_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// 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_CONFIG_DIR
configXDG_CONFIG_HOME
configKAGGLE_USERNAMEexport =your_user
🔐 secretKAGGLE_KEYexport =your_40_char_key
🔐 secretKAGGLE_API_TOKEN
configKAGGLE_MCP_SUBMISSION_CAP5 Per-competition daily submission budget
configKAGGLE_MCP_ENABLE_DESTRUCTIVE0 Exposes kaggle_delete_dataset / kaggle_delete_model
configKAGGLE_MCP_ENABLE_PUBLISH0 Allows creating public datasets
configKAGGLE_MCP_WORKDIR
configKAGGLE_MCP_TRANSPORT
// 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

41/41 tools missing one or more hints — kaggle_whoami (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); kaggle_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); kaggle_audit_log (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +38 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

7 tools perform destructive updates without destructiveHint — kaggle_download_competition_files deletes at line 230 (z.unlink()); kaggle_eda_competition deletes at line 251 (z.unlink()); kaggle_competition_kickoff deletes at line 317 (z.unlink())

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

2 tools describe read intent but their handlers mutate — kaggle_eda_competition (line 251: z.unlink()); kaggle_eda_dataset (line 97: z.unlink())

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

Tool inputs are validated

39/41 tool handlers declare input schemas (95%)

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

Tool handlers catch errors

35/41 tool handlers wrap calls in try/catch (85%)

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

3 tools have description/behavior mismatches: kaggle_eda_competition: description implies read-only but handler writes/deletes/executes; kaggle_eda_dataset: description implies read-only but handler writes/deletes/executes; kaggle_dataset_preview: 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 8 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/parkseokjune/kaggle-mcp?variant=verified)](https://m8ven.ai/mcp/parkseokjune/kaggle-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 33a5e69310adce3f5d245850a7961d8a5f822c84
code hash: dc8d6bb0eae44117f3178c57c67457369891837ba8fb5e0d7ef3f6c2ad4912ac
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