Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mtrakretech/kaggle-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/mtrakretech/kaggle-mcp/kaggle)<a href="https://agentmods.dev/mcp/mtrakretech/kaggle-mcp/kaggle"><img src="https://agentmods.dev/badge/mcp/mtrakretech/kaggle-mcp/kaggle/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/mtrakretech/kaggle-mcp/kaggle"><img src="https://agentmods.dev/badge/mcp/mtrakretech/kaggle-mcp/kaggle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kaggle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"kaggle": {
"command": "python",
"args": [
"/ABSOLUTE/PATH/TO/kaggle-mcp/kaggle_mcp.py",
"--stdio"
],
"env": {
"KAGGLE_USERNAME": "your_kaggle_username",
"KAGGLE_KEY": "your_kaggle_api_key",
"KAGGLE_API_TOKEN": "your_kaggle_api_key"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 14 lines scan A 4ecbe735b5fa
kaggle is an MCP server published in the GitHub repository mtrakretech/kaggle-mcp (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
modao
modao-proto-mcp - A Model Context Protocol server for Modao prototype generation, design tools, organization management, and HTML import functionality. Runs locally from the @modao-mcp/modao-proto-mcp npm package. Needs 1 environment variable to run.
kaggle
MCP server "kaggle", hosted remotely at www.kaggle.com, as configured in shepsci/kaggle-skill.
same
Persistent memory for AI coding agents. Local-first SQLite + vector search, 12 MCP tools. Runs locally from the @sgx-labs/same npm package. Needs 1 environment variable to run.
routara-mcp
OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai). Runs locally from the routara-mcp npm package. Needs 2 environment variables to run.
Kaggle-mcp
A Model Context Protocol (MCP) server for the Kaggle API. Runs locally from the mcp-server-kaggle Python package. Needs 2 environment variables to run.
thinking-prompts
MCP server "thinking-prompts" as configured in zdrjson/thinking-prompts-skill. Runs locally from the thinking-prompts npm package.