@tiberriver256/docs-to-mcp-cli

by Tiberriver256

2 178 downloads Not rated yet MIT license
GitHub

About

A CLI utility for turning your docs into a stdio MCP server

Details

License
MIT license

Explore

- Generates a self-contained, runnable MCP server from markdown docs
- Provides three tools: list_docs, get_doc, and search_docs
- Uses fuzzy matching for cross-document search
- Supports custom tool names and output directories
- Integrates with any MCP‑compatible AI assistant

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name @tiberriver256/docs-to-mcp-cli
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

You can install the tool globally:

npm install -g @tiberriver256/docs-to-mcp-cli

Or use it directly with npx:

npx @tiberriver256/docs-to-mcp-cli --docs "path/to/docs/*/.md" --packageName MyDocsServer

npm install

list_docs

Lists all available documents with a preview of their content

get_doc

Gets the full content of a specific document by its path

search_docs

Searches across all documents using fuzzy matching

docs-to-mcp-cli --docs "documentation/*/.md" --packageName APIDocsServer --toolName "My API" --outDir build

The generated MCP server provides the following tools to AI assistants:

- list_docs: Lists all available documents with a preview of their content
- get_doc: Gets the full content of a specific document by its path
- search_docs: Searches across all documents using fuzzy matching

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "@tiberriver256/docs-to-mcp-cli": {
            "docs-to-mcp-cli": {
                "command": "npx",
                "args": [
                    "@tiberriver256/docs-to-mcp-cli",
                    "--docs",
                    "path/to/docs/**/*.md",
                    "--packageName",
                    "MyDocsServer"
                ]
            }
        }
    }
}

McpServers

{
    "docs-to-mcp-cli": {
        "command": "npx",
        "args": [
            "@tiberriver256/docs-to-mcp-cli",
            "--docs",
            "path/to/docs/**/*.md",
            "--packageName",
            "MyDocsServer"
        ]
    }
}

A CLI tool that generates a self-contained, runnable MCP (Model Context Protocol) server that exposes markdown documentation via specific tools.

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to access external tools and data sources. By converting your documentation to an MCP server, you allow AI assistants to:

- Browse through your documentation
- Search for specific information
- Access the full content of any document
- Use your documentation to provide more accurate and contextual responses

Installation

You can install the tool globally:

npm install -g @tiberriver256/docs-to-mcp-cli

Or use it directly with npx:

npx @tiberriver256/docs-to-mcp-cli --docs "path/to/docs/*/.md" --packageName MyDocsServer

Usage

docs-to-mcp-cli --docs <pattern> --packageName <n> [--outDir <dir>] [--toolName <name>]

Options

- -d, --docs <pattern>: Glob pattern for markdown files (required)
- -p, --packageName <n>: Name for the generated MCP server (required)
- -o, --outDir <dir>: Output directory for the bundled server (default: "dist")
- -t, --toolName <name>: Name of the tool/package/library being documented (used in tool descriptions)
- -v, --version: Output the current version

Examples

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.