About Japan Parliament Search
Japan Parliament Search is a hosted MCP server for policy researchers, journalists, and compliance teams to search Japan’s National Diet records from 1947 onward. It supports speech and meeting searches with filters and official citation URLs, using live National Diet Library data.
Key features
- 01Full-text speech search
- 02Filters for speaker, chamber, meeting, and dates
- 03Meeting and committee search
- 04Excerpts or full speech text
- 05Official citation URLs
- 06Live National Diet Library data
Use cases
- 01Find a minister’s statements on a policy topic
- 02Locate when and where a debate occurred
- 03Gather cited Diet records for policy research
MCP support
Exposes speech and meeting searches as tools for MCP clients. Results include official citation URLs.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://kokkai-mcp.easakura.workers.dev/mcpclaude mcp add --transport http easakura-japan-parliament-search https://kokkai-mcp.easakura.workers.dev/mcp{"mcpServers":{"easakura-japan-parliament-search":{"type":"http","url":"https://kokkai-mcp.easakura.workers.dev/mcp"}}}Open in Cursor{"servers":{"easakura-japan-parliament-search":{"type":"http","url":"https://kokkai-mcp.easakura.workers.dev/mcp"}}}Open in VS Code{"mcpServers":{"easakura-japan-parliament-search":{"type":"http","url":"https://kokkai-mcp.easakura.workers.dev/mcp"}}}{"mcpServers":{"easakura-japan-parliament-search":{"serverUrl":"https://kokkai-mcp.easakura.workers.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://kokkai-mcp.easakura.workers.dev/mcphttps://kokkai-mcp.easakura.workers.dev/sseTools
Details
From the project READMEJapan Parliament Search MCP — 国会会議録検索
Give your AI agent access to every word spoken in Japan's National Diet since 1947.
This MCP server searches the official National Diet Library record system — ministerial statements, committee Q&A, and policy debates — the primary source for understanding Japanese government policy. Built for policy research, journalism, government-affairs, and compliance AI agents.
Why this server?
Japanese policy signals appear in Diet debates months before they become law or regulation. This data is public but effectively invisible to AI agents: Japanese-only, verbose, and buried in a legacy search interface. This server makes it queryable in one tool call.
Tools
search_speeches
Full-text search across all Diet speeches (1947–present). Filter by speaker, house (衆議院/参議院), meeting name, and date range. Returns speaker, position, party, date, an excerpt (or full text with full_text=true), and an official citation URL.
search_meetings
Find which plenary sessions and committees discussed a topic, and when — the bird's-eye view before drilling into individual speeches.
Example queries your agent can now answer
- 「生成AIについて文部科学大臣は国会でどう答弁している？直近のものを引用して」
- "When did the Diet last debate semiconductor subsidies, and in which committee?"
- 「インボイス制度に関する財務省side答弁を2026年に絞って要約して」
Data source & freshness
Official National Diet Library (国立国会図書館) Kokkai Kaigiroku API, fetched live on every call. Records go back to 1947 and include the most recent published sessions.
Pricing
Pay per tool call. One speech search or one meeting search = one event. No subscription, no minimum.
日本語
国会会議録（1947年〜最新）の答弁・質疑をAIエージェントから全文検索できるMCPサーバーです。発言者・院・委員会・期間での絞り込み、出典URL付き。政策調査・報道・渉外・コンプライアンス系AIに最適です。
Get started
This is a hosted (remote) MCP server, available on Apify Store:
👉 https://apify.com/e-asakura/japan-parliament-search-mcp
The store page includes setup instructions for Claude, ChatGPT, Cursor, and any MCP-compatible client. Pay-as-you-go: $0.02 per tool call, no subscription.
Built by Edward Asakura — Japanese data infrastructure for AI agents. Part of the SEKISHO series: subsidies / laws / parliament.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.