MCP Duty Pharma
MCPデューティファーマ
MCP Duty Pharmaは、夜間、週末、祝日も営業が法的に義務付けられている薬局を見つけるのに役立ちます。緊急時でも深夜の用事でも、このツールがあればいつでもどこに行けばよいかがわかります。
📋 システム要件
Python 3.10以上
Related MCP server: Hong Kong Health Data MCP Server
📦 依存関係
必要な依存関係をすべてインストールします。
# Using uv
uv sync必要なパッケージ
fastmcp : モデルコンテキストプロトコルサーバーを構築するためのフレームワーク
geoPy : 場所にアクセスし、ジオコーディング/逆ジオコーディングするための Python ライブラリ。
httpx : Python 用の HTTP クライアント。HTTP リクエストを行うためのシンプルで直感的な API を提供します。
すべての依存関係はpyproject.tomlで指定されます。
📑 目次
🛠️ MCP ツール
この MCP サーバーは、大規模言語モデル (LLM) に次のツールを提供します。
近くの薬局を探す
指定された住所からの距離順に、今日営業している最も近い薬局 10 軒を取得します。
🚀 はじめに
リポジトリをクローンします。
git clone https://github.com/lsaavedr/mcp-duty-pharma.git
cd mcp-duty-pharma📦 インストール
このMCPサーバーは、Claude Desktopまたは他の場所にインストールできます。このサーバーを使用するには、設定ファイルに以下の設定を追加してください。
JSON形式
{
"MCP Duty Pharma": {
"command": "uv",
"args": ["tool", "run", "mcp_duty_pharma"]
}
}yaml形式
mcpServers:
- name: MCP Duty Pharma
command: uv
args:
- tool
- run
- mcp_duty_pharma🔒 安全機能
レート制限: 使用制限に違反する過剰なリクエストを回避するために、各ジオコーディング呼び出しにはレート制限 (例: 1 秒の遅延) が設けられています。
エラー処理: geopy 例外 (タイムアウト、サービス エラー) をキャッチし、クラッシュする代わりに安全な [] 結果を返します。
📚 開発ドキュメント
このサーバーを拡張または変更したい場合は、次の手順に従ってください。
各ツールがどのように実装され、duty-pharma がどのように統合されているかについては、duty-pharma.py を確認してください。
境界ボックス、言語設定、高度なデータ抽出などの高度な使用方法については、geopy の公式ドキュメントを参照してください。
さらに多くのデータ ソースについては、地方自治体の API を参照してください。
Available Tools
1 toolget_nearby_duty_pharmaciesB
Get ten closest pharmacies on duty today, sorted by distance to the given address.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the tool returns 'ten closest pharmacies' and sorts by distance, it fails to describe critical behaviors such as response format, error handling, data freshness, rate limits, or authentication requirements. For a location-based query tool with zero annotation coverage, this leaves significant gaps.
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 is a single, well-structured sentence that efficiently conveys the core functionality: action, resource, quantity, constraints, and sorting. Every word earns its place with no redundancy or fluff, making it easy to parse and front-loaded with essential information.
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?
Given the tool's moderate complexity (location-based query with filtering), lack of annotations, and no output schema, the description is minimally complete. It covers the basic purpose and parameter intent but omits details on output structure, error cases, and operational constraints. It meets the bare minimum for understanding what the tool does but not how it behaves fully.
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?
The input schema has 0% description coverage, so the description must compensate. It adds meaning by explaining that the 'address' parameter is used to calculate distance and filter results, which goes beyond the schema's bare 'Address' title. However, it doesn't specify address format requirements, validation rules, or handling of ambiguous inputs, leaving some semantic gaps.
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 clearly states the tool's purpose: 'Get ten closest pharmacies on duty today, sorted by distance to the given address.' It specifies the verb ('Get'), resource ('pharmacies'), and key constraints ('ten closest', 'on duty today', 'sorted by distance'). However, with no sibling tools mentioned, it cannot demonstrate differentiation from alternatives.
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 provides no explicit guidance on when to use this tool versus alternatives. It implies usage for finding nearby duty pharmacies but offers no information about prerequisites, limitations, or scenarios where other tools might be more appropriate. With no siblings listed, this is a missed opportunity for basic context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
get_nearby_duty_pharmacies
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The tool name follows a clear verb_noun pattern (get_nearby_duty_pharmacies).
One tool is too few for a server with a domain like pharmacy duty information, as it lacks essential operations such as filtering by time, getting pharmacy details, or updating duty status. This severely limits agent functionality.
The tool surface is severely incomplete for the domain; it only provides a list of nearby duty pharmacies without supporting operations like checking specific pharmacy hours, verifying duty status, or managing pharmacy data, leading to significant gaps in agent workflows.
Maintenance
Related MCP Connectors
The MCP for the beauty, cosmetics and personal care sector
Jersey Open Data MCP — opendata.gov.je, the official statistics / open-data
Related MCP Servers
- -
- AlicenseAqualityCmaintenanceEnables querying of current A\&E waiting times, specialist outpatient waiting times, and general outpatient clinic quotas in Hong Kong using natural language through MCP.34MIT
- AlicenseBqualityBmaintenanceMCP server for Kenya health system — NHIF/SHA coverage, facility finder, community health workers, maternal health guidance, essential medicines.633 PyPIMIT
- AlicenseAqualityDmaintenanceThis MCP is capable of analyzing medical documents and prescriptions and giving patient all the medical info it needs and answering their questions8MIT