Fiftyone MCP Server vs Kaggle MCP
A side-by-side look at the Fiftyone MCP Server and Kaggle MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Fiftyone MCP Server for data science tools work as a local process; choose Kaggle MCP 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 Fiftyone MCP Server 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 want tools like
SDK, APP, SESSION.
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.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Science Tools | Data Science Tools |
| Quality signal | 56/100 · Good | 48/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | KAGGLE_USERNAMEKAGGLE_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 25 | 0 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 3 | 38 |
| Full listing | View Fiftyone MCP Server | View Kaggle MCP |
Tools & capabilities
Fiftyone MCP Server tools 3
SDKData operations that work everywhere (datasets, aggregations, schema, samples, operators, plugins). No App connection needed.APPControls the FiftyOne App UI in real time (set_view, open_panel, notify, select_samples, reload, and 25+ more). Requires a connected browser via `ctx.ops`.SESSIONBootstrap tools for starting a local App server (launch_app). Used from terminal environments.
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
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.
Fiftyone MCP Server
{
"mcpServers": {
"fiftyone-mcp-server": {
"command": "uvx",
"args": [
"fiftyone-mcp-server"
]
}
}
}
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"
}
}
}
}
Frequently asked questions
Fiftyone MCP Server is categorized under Data Science Tools and uses a local stdio subprocess. Kaggle MCP belongs to Data Science Tools and uses a local stdio subprocess. Pick Fiftyone MCP Server for data science tools work and Kaggle MCP 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.
Fiftyone MCP Server is listed as free. Auth: no auth required. Kaggle MCP has no declared pricing — check the project's own site. 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 fiftyone-mcp-server and kaggle-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Fiftyone MCP Server has a quality signal of 56/100 (Good) with 2 views, 0 installs and 25 GitHub stars. Kaggle MCP has 48/100 (Fair) with 1 views, 0 installs and 0 GitHub stars.