io.github.Seif-Sameh/Kaggle-mcp
kaggle-mcp
Is the io.github.Seif-Sameh/Kaggle-mcp MCP server down? No. Installed with mcp<2, it started and listed its tools on 2026-11-03.
MCP server for the Kaggle API: competitions, datasets, kernels, and models.
needs mcp<2 probed 2026-11-14 · unchanged since 2026-11-03
A plain install of the package stops at the import below. These tool definitions are from a second install with mcp<2, started in a container with the network off, on 2026-11-03.
MCP error -32000: Connection closed ModuleNotFoundError: No module named 'mcp.server.fastmcp'. This is mcp 2.x, where FastMCP was renamed to MCPServer (from mcp
- Run it
- uvx --with 'mcp<2' mcp-server-kaggle@0.1.1 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- kaggle-mcp 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Repository
- https://github.com/Seif-Sameh/Kaggle-mcp
- Registry
- active, updated 2026-06-11 · registry entry
- Changes
- 2 recorded, reachable in 0 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| datasets_list | 631 | 6 % |
| kernels_list | 557 | 6 % |
| competition_submissions | 507 | 5 % |
| dataset_download_file | 424 | 4 % |
| dataset_download_files | 421 | 4 % |
Compare this server with others.
More servers
Other registry entries on pypi.org, the ones next to this name; all of them.
- Graph-Mem io.github.Sathvik-1007/graphmem-mcp · crashed on start
- SatoshiAPI — Bitcoin Data via Lightning io.github.SatoshiAPI/satoshi-btc-api · crashed on start
- Scovant Core io.github.Scovant/scovant-core · needs args
- io.github.ScrapeGraphAI/scrapegraph-mcp · alive
- io.github.SemanticDataCharter/sdc-mapper · alive
- io.github.SemanticDataCharter/sdccdif · alive
- io.github.SemanticDataCharter/sdcdcatap · alive
- io.github.SemanticDataCharter/sdcdcatus · alive
Servers that mention kaggle or competitions or datasets.
- Safe Kaggle MCP io.github.parkseokjune/kaggle-mcp · needs env
- ai.baselight/baselight · no DNS
- Everyn ai.everyn/everyn · needs auth
- Klaaro ai.klaaro/klaaro · needs auth
- Webhound ai.webhound/webhound · needs auth
- Football Atlas app.futbolatlas/futbol-atlas · alive
- ai.smithery/hithereiamaliff-mcp-datagovmy · needs auth
- co.axiom/mcp · needs auth
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-03 08:46 | needs mcp<2 | 1.7 s | 39 | 17k | 9.8k |
| 2026-10-20 06:45 | crashed on start |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The package imports FastMCP from mcp.server.fastmcp. mcp 2.0, the Python SDK of 28 July 2026, renamed FastMCP to MCPServer, and the package asks for mcp with no upper bound, so a plain install (uvx, pip) gets mcp 2.x and the server stops at the import. Installed with mcp<2, it starts and lists its tools. The fix for the publisher: pin mcp<2 in the dependencies, for example mcp>=1.2,<2, and publish a new version, or move to MCPServer as the SDK's migration guide says. Until then, run it with uvx --with 'mcp<2'.
The cause and the fix, with the code before and after: ModuleNotFoundError: No module named 'mcp.server.fastmcp'