What is Library Mcp

library-mcp is an MCP server designed for interacting with Markdown knowledge bases, allowing users to manage and retrieve content organized in folders with Markdown files.

Use cases

Use cases include retrieving recent blog posts by tag, summarizing content from a specific time period, and managing a collection of Markdown knowledge bases for easier access and organization.

How to use

To use library-mcp, set up the server locally and organize your Markdown files in a folder structure. You can then utilize various tools to search for content by tags, text, slugs, URLs, or date ranges.

Key features

Key features include content search tools (get_by_tag, get_by_text, get_by_slug_or_url, get_by_date_range), tag management tools (search_tags, list_all_tags), and maintenance tools for managing your knowledge base.

Where to use

library-mcp can be used in personal projects, blogging, documentation, and any scenario where Markdown files are utilized to store and manage knowledge.

library-mcp is an MCP server for interacting with
Markdown knowledge bases. Basically, folders that may or may not have subfolders, that include
files with .md extension and start with metadata like:

----
title: My blog post
tags:
- python
- programming
url: /my-blog-post
---

# My blog post
Yesterday I was dreaming about...

The typical workflow in the current verison is to
retrieve recent content for a given tag, and then
discuss using that tag:

Get the next 50 posts with tag "executive",
then tell me what I should do about this problem
I am running into: ...

You can also do the same but by date ranges:

Summarize the blog posts I wrote in the past year.

You might reasonably ask “why not just upload your entire blog
into the context window?” and there are two places where this library
outperforms that approach:

1. My blog corpus is much larger than most model’s context windows today.
   Further, even if the context windows became exhaustively large, I wrote a lot
   of mediocre stuff in the past, so maybe omitting it’s a feature.
2. I have a number of distinct Markdown knowledge bases, and this lets me
   operate across them in tandem.

Finally, this is a hobby project, intended for running locally on your
laptop. No humans have been harmed using this software, but it does
work pretty well!

Tools

This MCP server exposes these tools.

Content Search Tools

Tools for retrieving content into your context window:

• get_by_tag - Retrieves content by tag
• get_by_text - Searches content for specific text
• get_by_slug_or_url - Finds posts by slug or URL
• get_by_date_range - Gets posts published within a date range

Tag Management Tools

Tools for navigating your knowledge base:

• search_tags - Searches for tags matching a query
• list_all_tags - Lists all tags sorted by post count and recency

Maintenance Tools

Tools for dealing with running the tool:

• rebuild - Rebuilds the content index,
  useful if you have added more content,
  edited existing content, etc

Setup / Installation

These instructions describe installation for Claude Desktop on OS X.
It should work similarly on other platforms.

1. Install Claude Desktop.

2. Clone library-mcp into
   a convenient location, I’m assuming /Users/will/library-mcp

3. Make sure you have uv installed, you can follow these instructions

4. Go to Cladue Desktop, Setting, Developer, and have it create your MCP config file.
   Then you want to update your claude_desktop_config.json.
   (Note that you should replace will with your user, e.g. the output of whoami.

    cd /Users/will/Library/Application Support/Claude
    vi claude_desktop_config.json
   

   Then add this section:

    {
      "mcpServers": {
        "library": {
          "command": "uv",
          "args": [
            "--directory",
            "/Users/will/library-mcp",
            "run",
            "main.py",
            "/Users/will/irrational_hugo/content"
          ]
        }
      }
    }
   

5. Close Claude and reopen it.

6. It should work…