Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Akebono MCP find a quiet Zen temple in Kyoto for a solo traveler who loves art"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent-ready Japanese travel spots — hidden gems, curated from SNS buzz, optimized for AI travel agents.
エージェント時代の旅行情報インフラ。SNSのバズから「一般的すぎない特別な体験スポット」を厳選し、AIエージェントが直接使える形で提供するMCPサーバー。
現在のフォーカスエリア: 名古屋（大須・栄・金山・久屋大通・矢場町） 昭和レトロ・古民家リノベ・隠れ家など、非日常体験のできる穴場スポットを収集中。
recommend_temples自然言語クエリに基づいて京都の寺院をスコア付きで推薦する。
入力例:
"40代夫婦・歴史好き・混雑嫌い・半日"
"一人旅・禅・静かな場所・アート好き"
"子供連れ・無料・世界遺産"
出力例:
{
"query": "40代夫婦・歴史好き・混雑嫌い・半日",
"results": [
{
"name": "建仁寺",
"slug": "kenninji",
"score": 88,
"reason": "混雑が少ない・歴史好きにおすすめ。京都最古の禅寺。双龍図は2002年作の現代アートで驚きがある。",
"tags": ["禅", "アート", "歴史", "静か", "双龍図"],
"crowd_level": "medium",
"price": "600円",
"topics": ["天井を埋め尽くす「双龍図」は実は21世紀のアート", "日本初の「禅」と「お茶」の聖地"]
}
]
}get_temple_detail特定の寺院の詳細情報とトピック一覧を取得する。
入力: slug（例: "kenninji"）
Related MCP server: Edition Intelligence Platform
git clone https://github.com/YOGi-Seto/akebono-mcp
cd akebono-mcp
npm install~/.claude/claude_desktop_config.json に追記:
{
"mcpServers": {
"akebono": {
"command": "node",
"args": ["/path/to/akebono-mcp/src/index.js"]
}
}
}スラッグ | 寺院名 |
toji | 東寺 |
enryakuji | 延暦寺 |
chionin | 知恩院 |
nishihonganji | 西本願寺 |
kenninji | 建仁寺 |
kiyomizudera | 清水寺 |
名古屋エリアのスポットを50件以上に拡充
他都市への展開（大阪・京都・福岡など）
リアルタイム混雑情報
利用データによるスコア精度向上
日本全国展開
特定の寺院の詳細情報とトピック一覧を取得する。
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | 寺院のスラッグ（toji / enryakuji / chionin / nishihonganji / kenninji / kiyomizudera） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses what the tool returns (detailed information and topic list), but lacks operational details such as error handling (e.g., invalid slug), rate limits, or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of a single efficient sentence that immediately states the action and target. No extraneous words or redundant explanations are present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter retrieval tool with complete schema coverage, the description adequately covers the functional scope. While it does not describe the output format (absent output schema), this is acceptable per evaluation rules.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing detailed examples of slug values. The description does not redundantly explain the parameter, meeting the baseline expectation when the schema is self-documenting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific language (取得する/retrieve) with a clear resource (特定の寺院の詳細情報とトピック一覧/specific temple details and topic list). While it implies differentiation from 'recommend_temples' by emphasizing a 'specific' temple, it does not explicitly contrast the two tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states what the tool does but provides no explicit guidance on when to use it versus the sibling tool 'recommend_temples', nor does it mention prerequisites like needing to know the temple slug beforehand.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
自然言語のクエリに基づいて京都の寺院をスコア付きで推薦する。旅行者のプロファイル・希望・条件を自由に入力できる。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 旅行者のプロファイルや希望（例：「40代夫婦・歴史好き・混雑嫌い・半日」「一人旅・禅・静かな場所」「子供連れ・無料・世界遺産」） | |
| limit | No | 返す件数（デフォルト5件） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behavioral trait (returned temples are scored/ranked) and natural language input capability beyond what annotations provide. No annotations exist to cover read-only status; description could clarify safety/permissions but 'recommend' implies read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tightly constructed sentences: first establishes purpose and method, second clarifies input flexibility. No redundancy or wasted words. Perfectly front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Appropriate for a 2-parameter tool with simple structure. Mentions scoring which hints at output format despite lacking output schema. Could explicitly mention return structure (list of temple objects with scores) for perfect completeness but adequate as-is.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed examples in the query parameter. Description reinforces the free-form nature of input but adds minimal semantic detail beyond the schema's comprehensive examples. Baseline 3 appropriate for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Excellent specificity: states the tool recommends (スコア付きで推薦) Kyoto temples based on natural language queries. Distinguishes from sibling get_temple_detail by emphasizing recommendation/scoring behavior versus detail retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage by describing flexible input options (traveler profiles, conditions) but lacks explicit guidance on when to use this versus get_temple_detail (e.g., 'use this for personalized recommendations, use get_temple_detail for specific temple facts').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_temple_detailrecommend_templesScored across 2 tools
The two tools have clearly distinct purposes: one retrieves detailed information for a specific temple, while the other provides recommendations based on natural language queries and traveler profiles. There is no overlap in functionality, making it easy for an agent to choose the correct tool for each task.
Both tools follow a consistent verb_noun naming pattern (get_temple_detail and recommend_temples), using snake_case throughout. The naming is predictable and readable, with no deviations or mixed conventions.
With only two tools, the server feels under-scoped for a domain like Kyoto temple information and recommendations. This limited set may force agents to work around gaps, such as lacking operations for listing temples, updating data, or handling user preferences beyond recommendations.
The tool surface is significantly incomplete for the apparent domain of Kyoto temple exploration. While it offers retrieval and recommendation, it lacks essential operations like listing temples, filtering by criteria, or managing user profiles, which could lead to agent failures in broader workflows.
AI-verified knowledge base with trust scoring, temporal facts, and skill cards.
Memory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.
Real-time AI intelligence signals and temporal knowledge graph for agent economy
Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
