LeashIndex Get the report

Index / storage

io.github.Seif-Sameh/Kaggle-mcp

io-github-seif-sameh-kaggle-mcp declares 39 capabilities across 39 tools, with 2 critical issues.

89/100 exposureHigh exposure

Manifest recorded 2026-10-14 from tools/list answered by the PyPI package mcp-server-kaggle==0.1.1 (published to PyPI as mcp-server-kaggle, listed in the official MCP registry as io.github.Seif-Sameh/Kaggle-mcp 0.1.1), run in an isolated container with no network access and placeholder credentials. The date changes only when the manifest does. Not verified by a maintainer.

Note. Installed with the MCP Python SDK held below version 2.0. With the newest SDK this version of the package stopped before it could list its tools.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 39 tools

39 of 39 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 3 of 39 tools

3 tools are classified as irreversible and declare no limit.

high · no-expiry · All 39 tools

39 of 39 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 39 tools

39 of 39 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 23 of 39 tools

23 tools can modify data and declare no limit.

low · uncapped-read · 13 of 39 tools

13 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
competitions_listread inferred
competition_list_filesread inferred
competition_download_filewrite assumed
competition_download_fileswrite assumed
competition_submitwrite assumed
competition_submissionsread inferred
competition_leaderboard_viewread inferred
competition_leaderboard_downloadwrite assumed
datasets_listread inferred
dataset_metadatawrite assumed
dataset_list_filesread inferred
dataset_statusread inferred
dataset_download_filewrite assumed
dataset_download_fileswrite assumed
dataset_createwrite inferred
dataset_initializewrite assumed
dataset_create_versionwrite inferred
kernels_listread inferred
kernel_list_filesread inferred
kernel_initializewrite assumed
kernel_pushwrite inferred
kernel_pullwrite assumed
kernel_outputwrite assumed
kernel_statusread inferred
models_listread inferred
model_getread inferred
model_initializewrite assumed
model_createwrite inferred
model_updatewrite inferred
model_deletedelete inferred
model_instance_getread inferred
model_instance_initializewrite assumed
model_instance_createwrite inferred
model_instance_updatewrite inferred
model_instance_deletedelete inferred
model_instance_version_createwrite inferred
model_instance_version_downloadwrite assumed
model_instance_version_fileswrite assumed
model_instance_version_deletedelete inferred
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.