Kensho Kaku

io.github.atushi1841v1.0.0Updated Oct 3, 2026

Japan X/Twitter sweepstakes data from ken-kaku.com. 3 tools: search, history, prize movers.

VerifiedSTDIODesktop onlyData & AnalyticsWeb Search & Scraping

Overview

AI-generated overview

Read-only access to a Japanese X/Twitter sweepstakes dataset, with tools to search current sweeps, view prize price history, and find top prize movers.

What it does
Exposes the kensho Japan X/Twitter sweepstakes dataset from ken-kaku.com through three read-only tools. current_sweep returns the latest sweep matching a keyword such as a prize, brand, or URL substring. sweep_history returns a price time series for a keyword, oldest first, with a configurable limit. top_prize_movers ranks the biggest prize value changes in JPY, optionally filtered to increases or decreases.
When to use it
Useful when you want an assistant to look up Japanese sweepstakes campaigns, check how a prize's listed value has changed over time, or surface the largest recent prize value movements. It is a niche data source, best added alongside other kensho sweepstakes sources rather than on its own.
Requirements
Runs locally as a stdio MCP process, or over streamable-http at /mcp when started with the --http flag. Needs Python and the fastmcp package version 3.0.0 or later. The README states no network access, API key, or account is required. Desktop only.
Before you install
The data is a bundled snapshot file rather than a live feed, so results may be stale. The README describes a revenue sharing model with a platform fee and revenue from external queries, which is a commercial arrangement rather than a technical risk. All three tools are read-only.

Installation

In SourceWeft

  1. Open Kensho Kaku in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

kensho-kaku — Japan Sweepstakes MCP Server

Read-only MCP server exposing the kensho Japan X/Twitter sweepstakes dataset from ken-kaku.com (additional source for Kensho sweepstakes collection).

Tools

ToolDescription
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

Data

  • Source: data/accumulated.jsonl (estimated 500+ observations, snapshot 2026-09-28)
  • Source: ken-kaku.com sweepstakes collection (additional to knshow, kenshou.club, cp.meikan)
  • No network, no API key, no account required

Run

bash
python server/server.py          # stdio MCP transportpython 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:

bash
npx -y @anthropic-ai/mcpb pack . dist/kensho-kaku.mcpb

Revenue Model

This MCP Connector follows the Kensho revenue sharing model:

  • 20% to Apify (platform fee)
  • PPE model continues for internal operations
  • Revenue generated from external queries via Apify MCP integration

Integration Notes

The kensho-kaku MCP Connector serves as an additional data source for the main Kensho sweepstakes collection, complementing the existing knshow.com, kenshou.club, and cp.meikan.org sources. It provides specialized coverage of the Ken-Kaku.com sweepstakes ecosystem.

Source: README.md at commit b1c51ca

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 3, 2026