Gone. Gone from the registry since 12 Oct.
Kensho Sweep
Japan X/Twitter sweepstakes campaign data (1133 records). Tools: search, history, movers.
Runs on your machine from its package; the steps are below.
What it does
- Reads
- Writes
- High impact
At most: only reads or looks up information.
What it costs
FreeOdel charges nothing per call. The publisher may charge for its own service.
Runs locally over stdio
This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).
Distributed as an MCP bundle (`https://github.com/atushi1841/kensho-sweep-mcp/releases/download/v1.0.0/server.mcpb`) — download it and import the bundle in your MCP client.
kensho-sweep-mcp — Japan X/Twitter Sweepstakes MCP Server
Read-only MCP server exposing the kensho Japan X/Twitter sweepstakes dataset collected from knshow.com, kenshou.club, ken-kaku.com, and cp.meikan.org.
Tools
| Tool | Description |
|---|---|
current_sweep(keyword) | Latest sweep matching keyword (prize, brand, URL substring) |
sweep_history(keyword, limit=50) | Price time series (oldest first) |
top_prize_movers(direction=None, limit=10) | Biggest |delta JPY| prize value movers, optional up/down filter |
Data
- Source:
data/accumulated.jsonl(1133 observations, snapshot 2026-09-27) - Sources: knshow.com, kenshou.club, ken-kaku.com, cp.meikan.org
- No network, no API key, no account required
Run
python server/server.py # stdio MCP transport
python server/server.py --http # streamable-http at /mcp
Requires fastmcp>=3.0.0 (see requirements.txt).
MCP Bundle
manifest.json follows the MCPB v0.4 spec. Pack with:
npx -y @anthropic-ai/mcpb pack . dist/kensho-sweep-mcp.mcpb
