About library-mcp
An MCP server for working with Markdown knowledge bases, aimed at users who want to search blog posts or notes stored in local folders. It retrieves posts by tag, text, date range and slug, and browses tags across the knowledge base. It is a personal project meant to run locally.
Key features
- 01Retrieve content by tag
- 02Search content by text
- 03Get posts by date range
- 04Find posts by slug or URL
- 05Search and list tags
- 06Rebuild the content index
Use cases
- 01Retrieving recent posts by tag for discussion
- 02Summarizing posts written within a time period
- 03Searching across several Markdown knowledge bases
MCP support
The server exposes content retrieval, tag management and index rebuild tools to MCP clients, reading content from local Markdown knowledge bases.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMElibrary-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:
- 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.
- 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 tagget_by_text- Searches content for specific textget_by_slug_or_url- Finds posts by slug or URLget_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 querylist_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.
-
Install Claude Desktop.
-
Clone library-mcp into a convenient location, I'm assuming
/Users/will/library-mcp -
Make sure you have
uvinstalled, you can follow these instructions -
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 replacewillwith your user, e.g. the output ofwhoami.cd /Users/will/Library/Application Support/Claude vi claude_desktop_config.jsonThen add this section:
{ "mcpServers": { "library": { "command": "uv", "args": [ "--directory", "/Users/will/library-mcp", "run", "main.py", "/Users/will/irrational_hugo/content" ] } } } -
Close Claude and reopen it.
-
It should work...
Comments
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.