// SCAN REPORT

Mcp Kaggle Tool

8 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

2 can modify or destroy data

6 read-only

8 tools total

Community server · catalogue entry verified 30/06/2026

How to control Mcp Kaggle Tool ↓

TOOL MAP

What Mcp Kaggle Tool exposes to your agents

Read (6) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mcp Kaggle Tool tools

Execute · High kaggle_run_notebook This tool triggers execution of code (a Kaggle notebook) whose effects depend entirely on the notebook's contents and arguments. Write · Medium kaggle_create_notebook This tool creates a new notebook resource in Kaggle, which is a reversible write operation.

2 of Mcp Kaggle Tool's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Kaggle Tool

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Kaggle Tool, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "kaggle_create_notebook": {
    "limits": [
      {
        "counter": "kaggle_create_notebook_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "kaggle_auth_check": {
    "limits": [
      {
        "counter": "kaggle_auth_check_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Kaggle Tool — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP KAGGLE TOOL →

Instant setup, no code required.

FULL CATALOGUE

All 8 Mcp Kaggle Tool tools

EXECUTE 1 tools

Execute kaggle_run_notebook Run/execute a Kaggle notebook

WRITE 1 tools

Write kaggle_create_notebook Create a new Kaggle notebook

READ 6 tools

Read kaggle_auth_check Check if Kaggle API credentials are configured Read kaggle_download_notebook_output Download the output of a completed notebook Read kaggle_get_notebook_status Get the status of a notebook execution Read kaggle_list_competitions List Kaggle competitions Read kaggle_list_notebooks List your Kaggle notebooks (kernels) Read kaggle_search_datasets Search for Kaggle datasets

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Kaggle Tool

How do I prevent bulk modifications through Mcp Kaggle Tool? +

The Mcp Kaggle Tool server has 1 write tools including kaggle_create_notebook. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Kaggle Tool.

How many tools does the Mcp Kaggle Tool MCP server expose? +

8 tools across 3 categories: Execute, Read, Write. 6 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Mcp Kaggle Tool? +

Register the Mcp Kaggle Tool MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Kaggle Tool tool call.

Deterministic rules across all 8 Mcp Kaggle Tool tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP KAGGLE TOOL →

Instant setup, no code required.

8 Mcp Kaggle Tool tools catalogued and risk-classified — across an index of 43,000+ MCP servers.