Edition Intelligence Platform
EDITION 智能平台
为在日本运营的 AI 智能体提供的缺失基础设施。
记忆 API + 法规检查 API + 程序化知识 + MCP 服务器 —— 专为日本商业环境打造。
问题所在
与日本企业合作的 AI 智能体常会遇到通用工具无法解决的障碍:
敬语 (Keigo):像 “ワインをお持ちすれば喜ばれるかと存じます” 这样的句子隐藏了主语,使用了多层敬语,并表达了不确定性 —— 通用 NLP 会将其视为噪声
隐性协议:日本商业沟通很少直接表达意图
法规迷宫:10 多个行业存在重叠的国家/地方性法规,且大多数文档仅提供日语版本
缺乏持久化上下文:智能体在会话之间会丢失所有记忆
Related MCP server: japan-ux-mcp
本平台的功能
1. 记忆 API — 具备日语感知能力的持久化记忆
存储片段,通过敬语分析、社会层级检测和置信度评分自动提取结构化事实。
Input: "佐藤部長にはワインをお持ちすれば喜ばれるかと存じます"
Output:
Subject: 佐藤 (役職: 部長)
Predicate: 好む
Object: ワイン
Keigo: Level 2 (尊敬語)
Hierarchy: superior
Confidence: 0.7 (推測 — not stated as fact)
Tense: present三层架构:
片段 (Episodes) — 原始对话日志
事实 (Facts) — 结构化知识(通过 LLM 自动提取)
上下文 (Context) — 每个实体/主题的摘要状态
2. 法规 API — 10 个行业 + 游客规则
预置法规数据库,涵盖:
电商网站、房地产、人力资源、餐饮服务、建筑
医疗保健、金融、交通、教育、住宿
游客类别:签证、免税、过境、医疗、礼仪
所有 10 个行业均包含分步程序指南(共 65 个步骤)—— 涵盖操作内容、方式、地点、所需文件、费用、时间表和常见陷阱。
curl -X POST /api/v1/regulation/check \
-d '{"industry": "food_service", "query": "What licenses do I need to open a restaurant in Tokyo?"}'3. MCP 服务器 — 为 Claude、Cursor 等提供的 8 个工具
工具 | 描述 |
| 存储片段 + 自动提取事实 |
| 跨片段语义搜索 |
| 列出结构化事实 |
| 获取上下文摘要 |
| 从文本中提取事实 |
| 按行业检查法规 |
| 列出涵盖的行业 |
| 游客法规查询 |
快速入门
后端
git clone https://github.com/hiroshic9-png/edition.git
cd edition
python3 -m venv venv && source venv/bin/activate
pip install fastapi 'uvicorn[standard]' pydantic sqlalchemy aiosqlite chromadb python-dotenv google-genai
# Set your LLM key (any one of these)
echo 'GEMINI_API_KEY=your_key' > .env
# or ANTHROPIC_API_KEY or OPENAI_API_KEY
python -m uvicorn backend.api.main:app --reload
# → http://localhost:8000/docsMCP 服务器 (适用于 Claude Desktop / Cursor)
cd mcp-server && npm install && npm run build && npm start添加到 claude_desktop_config.json:
{
"mcpServers": {
"edition": {
"command": "node",
"args": ["/path/to/mcp-server/dist/index.js"],
"env": {
"EDITION_API_URL": "http://localhost:8000",
"EDITION_API_KEY": "your_api_key"
}
}
}
}API 端点
记忆
方法 | 端点 | 描述 |
POST |
| 存储片段 (设置 |
POST |
| 语义搜索 |
POST |
| 添加事实 |
GET |
| 列出事实 |
GET |
| 上下文摘要 |
POST |
| 从文本中提取事实 |
法规
方法 | 端点 | 描述 |
POST |
| 检查法规 (10 个行业 + LLM RAG) |
GET |
| 列出行业 |
GET |
| 游客类别 |
技术栈
层级 | 技术 |
API | FastAPI (Python) |
记忆存储 | SQLite + ChromaDB (向量搜索) |
MCP | TypeScript SDK v1.29 |
LLM | Gemini / Claude / GPT (事实提取 + RAG) |
为什么不用 Mem0 / Letta / Zep?
这些都是优秀的通用记忆工具。但它们无法:
解析日语敬语级别 (丁寧語 / 尊敬語 / 謙譲語)
从敬语模式中检测隐性社会层级
根据日语表达模式(断定 vs 推测 vs 传闻)进行置信度评分
包含日本法规数据库
本项目存在的意义在于:日本商业环境在结构上是独特的,智能体需要专门构建的基础设施来应对这些挑战。
许可证
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceJapanese calendar API for AI agents. Provides Rokuyo, Rekichu, Eto, 24 Solar Terms, and fortune judgments. MCP + REST API.5MIT
- AlicenseAqualityBmaintenanceProvides Japanese UX conventions as an MCP server to help AI generate correct Japanese UI elements like proper name order, furigana, phone formats, and polite language. It includes tools for form generation, validation, keigo suggestions, and cultural adaptation for developers building Japanese-facing products.6214MIT
- AlicenseNot gradedqualityBmaintenanceTorify gives AI agents the Japanese locale primitives that standard libraries lack — imperial era date conversion (wareki), qualified invoice number validation with NTA registry lookup, corporate number lookup (法人番号), postal code resolution, name romanization (Hepburn), and kanji-to-kana conversion via Yahoo! JLP. 31 endpoints total. No authentication required for MCP. Pay-per-call $0.02/call viaMIT
- FlicenseNot gradedqualityDmaintenanceProvides AI agents with comprehensive Japanese market intelligence through 27 MCP tools, covering corporate data, macroeconomics, financials, and environmental data from 14 integrated sources.
Related MCP Connectors
MCP server for Japan geodata: cadastral lot numbers (chiban) and reverse geocoding, for AI agents.
Japan Law MCP — Japanese national laws & ordinances via the e-Gov Law API.
Raw Japanese regulatory data for AI agents: pension, gazette, gBizINFO. x402-metered (USDC).
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hiroshic9-png/edition-api'
If you have feedback or need assistance with the MCP directory API, please join our Discord server