mcpField
M
MCPInstructionServer

MCPInstructionServer

Local
github.com/MartinSchlottAI & Agents0Updated 85w ago

About MCPInstructionServer

MCPInstructionServer is a TypeScript MCP server for AI assistants to discover and read Markdown instruction documents from a directory. It recursively indexes files, extracts summaries from titles and opening paragraphs, and restricts access to the configured directory.

Key features

  1. 01Recursively scan Markdown instruction files
  2. 02Extract summaries from titles and first paragraphs
  3. 03List instructions with their IDs
  4. 04Read full content by instruction ID
  5. 05Restrict access to the configured directory

Use cases

  1. 01Organize AI prompts and operating guidance
  2. 02Retrieve project standards on demand
  3. 03Reuse structured instructions across AI assistants

MCP support

It provides MCP clients with the listInstructions and readInstruction tools to list summaries and retrieve selected documents.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCPInstructionServer

A TypeScript MCP (Model Context Protocol) server for AI assistants to discover and access structured markdown instructions.

Overview

MCPInstructionServer enables AI assistants like Claude to access a library of markdown-based instructions through a standardized interface. By organizing instructions as markdown files, you can:

  • Create a centralized knowledge base for AI prompting
  • Maintain versioned, structured guidance documents
  • Allow AI assistants to search and retrieve specific instructions on-demand
  • Establish consistent patterns for AI-assisted tasks

How It Works

The server indexes markdown files in a specified directory (and its subdirectories), treating each file as an instruction document. The server extracts each document's title and first paragraph to create searchable summaries.

AI assistants can then:

  1. List all available instructions with their summaries
  2. Request specific instructions by ID

Features

  • Simple filesystem-based storage: Just markdown files in directories
  • Recursive directory scanning: Organize instructions in a hierarchical folder structure
  • Path security: Prevents directory traversal and access to files outside the allowed directory
  • Automatic summary extraction: Pulls the H1 title and first paragraph from each document
  • Model Context Protocol support: Compatible with AI assistants that implement MCP

Prerequisites

  • Node.js 18+ (for ESM support)
  • npm or yarn
  • Basic familiarity with TypeScript and markdown

Installation

# Clone the repository
git clone https://github.com/yourusername/MCPInstructionServer.git
cd MCPInstructionServer

# Install dependencies
npm install

# Build the project
npm run build

Usage

Starting the Server
# Start with path to your instructions directory
npm start -- /path/to/instructions

# Or directly with node
node dist/index.js /path/to/instructions
Creating Instructions

Instructions are simply markdown files with the .md extension. Each file should follow this structure:

# Instruction Title

Brief description of this instruction's purpose. This first paragraph will be used as the summary when listing instructions.

## Details

Additional sections with more detailed information...

## Examples

Usage examples, code samples, etc.
Directory Structure Example
instructions/
├── api/
│   ├── authentication.md
│   └── rate-limiting.md
├── design/
│   ├── color-system.md
│   └── typography.md
└── general/
    ├── code-review.md
    └── git-workflow.md
Accessing Instructions

The server provides two MCP tools:

1. listInstructions

Returns a list of all available instructions with their IDs and summaries.

Example response:

id: api/authentication
summary: Authentication API - This document outlines the authentication protocol used in our system.

id: design/typography
summary: Typography Guidelines - This guide explains our typographic scale and usage rules.
2. readInstruction

Takes an instruction ID and returns the full content of the corresponding instruction.

Example request: { "id": "api/authentication" }

Development

# Run in development mode with auto-restart
npm run dev -- /path/to/instructions

# Run tests
npm test

Security Considerations

  • The server validates all paths to prevent directory traversal attacks
  • Only files within the specified instructions directory can be accessed
  • No writing capabilities are provided, only reading is allowed

License

MIT

Contributing

Contributions welcome! Please feel free to submit a Pull Request.

Comments

Markdown supported

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.