MCP Docs Server

Provides direct access to local Markdown project docs via MCP tools for overview and search.

python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "unlock-mcp-mcp-docs-server": {
      "command": "/opt/homebrew/bin/python3.11",
      "args": [
        "/path/to/mcp-docs-server/mcp_context_server.py"
      ]
    }
  }
}

You can run a lightweight MCP server that serves your local Markdown documentation directly to your MCP clients. It provides two simple tools to access your content: one to list section titles and another to search across sections. This makes project context readily available to language models without complex vector stores or embeddings.

How to use

Use your MCP client to connect to the local Docs Server you configured. You will have two primary capabilities: get a quick overview of your docs and search for topics across the document. Get overview: request the list of section titles. Search content: query terms like product names, authentication flows, or setup steps and review matching sections. These tools respond with structured results you can present to the model or use in prompts.

How to install

Prerequisites you need before installing the server are straightforward.

Python 3.11+
MCP client (Claude Desktop, cline, etc.)

How to install

Follow these concrete steps to set up the server and prepare your documentation.

Clone the project and move into it.
Install Python dependencies.
Create your documentation file at the project root named context.md.

How to install

Configure the MCP client for GUI usage (Claude Desktop) using the provided shell wrapper.
For GUI clients, make the wrapper executable and install the server.
For CLI/cline clients, add a stdio MCP config that points to the Python interpreter and the server script.

Available tools

get_context_overview

Lists all section titles of the local context.md document so you can see the document structure at a glance.

search_context

Searches across all sections of the local context.md to find relevant content based on your query.