広告掲載
MCP.so
ログイン

MCPInstructionServer MCP Server

@MartinSchlott

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

MartinSchlott

MCPInstructionServer MCP Server について

概要はまだありません

#mcp#instruction-server#ai-assistant

MCPInstructionServer MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "MCPInstructionServer": {
      "command": "node",
      "args": [
        "dist/index.js",
        "/path/to/instructions"
      ]
    }
  }
}

MCPInstructionServer MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCPInstructionServer?

MCPInstructionServer is a TypeScript MCP server that lets AI assistants discover and access structured markdown instructions stored in a local directory. It indexes markdown files, extracts titles and summaries, and provides two MCP tools—listInstructions and readInstruction—for listing available documents and retrieving their full content.

How to use MCPInstructionServer?

Start the server by passing the path to your instructions directory: npm start -- /path/to/instructions or node dist/index.js /path/to/instructions. Instructions are plain .md files with an H1 title and a first‑paragraph summary. The server exposes two MCP tools: listInstructions to see all instruction IDs and summaries, and readInstruction with an id parameter to get the full document.

Key features of MCPInstructionServer

  • Simple filesystem‑based storage using markdown files in directories
  • Recursive directory scanning for hierarchical organization
  • Path security prevents directory traversal and access outside the allowed directory
  • Automatic extraction of H1 title and first paragraph as summaries
  • Model Context Protocol support for compatible AI assistants

Use cases of MCPInstructionServer

  • Provide an AI assistant with a centralized, versioned library of prompting guidelines.
  • Let Claude or other MCP‑compatible AIs search and retrieve specific instruction documents on demand.
  • Establish consistent, structured markdown guidance for AI‑assisted tasks across a team.
  • Maintain separate instruction sets (e.g., authentication, design, code review) in a folder hierarchy.

よくある質問

1

What runtime does MCPInstructionServer require?

Node.js 18+ (for ESM support) and npm or yarn.

2

How are instructions stored and organized?

Instructions are simply `.md` files in a specified directory. The server scans recursively, so you can nest files in folders. Each file must have an H1 title and a first paragraph used as the summary.

3

Is there any writing capability?

No. MCPInstructionServer only provides read‑only access. It has no tools for creating, editing, or deleting files.

4

How does the server handle security?

It validates all requested paths to prevent directory traversal attacks and ensures only files within the specified instructions directory can be read.

5

Which MCP tools does the server provide?

Two tools: `listInstructions` (returns a list of document IDs and their summaries) and `readInstruction` (requires an `id` string and returns the full markdown content).

コメント

「その他」の他のコンテンツ

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

ICSS

chokcoco

不止于 CSS

20.7K

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K
P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

広告掲載