Kaggle MCP vs Stats Compass
A side-by-side look at the Kaggle MCP and Stats Compass MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Kaggle MCP for data science tools work as a local process; choose Stats Compass for data science tools as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Kaggle MCP when
- You need dedicated capabilities in the Data Science Tools domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
KAGGLE_USERNAME, KAGGLE_API_KEY. - You want tools like
competitions_list, competition_list_files, competition_download_file.
Choose Stats Compass when
- You need dedicated capabilities in the Data Science Tools domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
STATS_COMPASS_PORT, STATS_COMPASS_SERVER_URL, STATS_COMPASS_MAX_UPLOAD_MB.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Science Tools | Data Science Tools |
| Quality signal | 48/100 · Fair | 44/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | KAGGLE_USERNAMEKAGGLE_API_KEY | STATS_COMPASS_PORTSTATS_COMPASS_SERVER_URLSTATS_COMPASS_MAX_UPLOAD_MB |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 17 |
| Directory activity | 1 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 38 | Not listed |
| Full listing | View Kaggle MCP | View Stats Compass |
Tools & capabilities
Kaggle MCP tools 38
competitions_listList and search available competitionscompetition_list_filesList all files in a competitioncompetition_download_fileDownload a specific competition filecompetition_download_filesDownload all competition filescompetition_submitSubmit predictions to a competitioncompetition_submissionsView your submission historycompetition_leaderboard_viewView the competition leaderboardcompetition_leaderboard_downloadDownload leaderboard datadatasets_listSearch and filter datasetsdataset_metadataGet dataset metadatadataset_list_filesList files in a datasetdataset_statusCheck dataset processing status- +26 more on the listing page
Stats Compass tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Kaggle MCP
{
"mcpServers": {
"kaggle-mcp": {
"command": "uvx",
"args": [
"mcp-server-kaggle"
],
"env": {
"KAGGLE_USERNAME": "YOUR_KAGGLE_USERNAME_HERE",
"KAGGLE_API_KEY": "YOUR_KAGGLE_API_KEY_HERE"
}
}
}
}
Stats Compass
{
"mcpServers": {
"stats-compass": {
"command": "uvx",
"args": [
"stats-compass-mcp"
],
"env": {
"STATS_COMPASS_PORT": "YOUR_STATS_COMPASS_PORT_HERE",
"STATS_COMPASS_SERVER_URL": "YOUR_STATS_COMPASS_SERVER_URL_HERE",
"STATS_COMPASS_MAX_UPLOAD_MB": "YOUR_STATS_COMPASS_MAX_UPLOAD_MB_HERE"
}
}
}
}
Frequently asked questions
Kaggle MCP is categorized under Data Science Tools and uses a local stdio subprocess. Stats Compass belongs to Data Science Tools and uses a local stdio subprocess. Pick Kaggle MCP for data science tools work and Stats Compass for data science tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Kaggle MCP has no declared pricing — check the project's own site. Stats Compass is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add kaggle-mcp and stats-compass as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Kaggle MCP has a quality signal of 48/100 (Fair) with 1 views, 0 installs and 0 GitHub stars. Stats Compass has 44/100 (Fair) with 3 views, 0 installs and 17 GitHub stars.