Library MCP
A local server to query and interact with Markdown knowledge bases by tags, text, slug, or date.
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:
- 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...
Servidores relacionados
Epicor Kinetic MCP Server by CData
A read-only MCP server by CData that enables LLMs to query live data from Epicor Kinetic.
@exerciseapi/mcp-server
Official MCP server for exerciseapi.dev — search 2,198+ exercises across 12 categories
Apache Gravitino
Access Apache Gravitino, a high-performance, federated metadata lake for data and AI.
Snapchat Ads by CData
A read-only MCP server for querying live Snapchat Ads data using the CData JDBC Driver.
CData Reckon Accounts Hosted
A read-only MCP server by CData that enables LLMs to query live data from Reckon Accounts Hosted. Requires a separate CData JDBC Driver.
DICOM MCP Server
Enables AI assistants to query, read, and move data on DICOM servers such as PACS and VNA for medical imaging.
Knowledge Graph Memory Server
Enables project memory using a Kuzu-powered knowledge graph.
OpenSearch MCP Server
An MCP server for interacting with OpenSearch clusters, configured via environment variables.
Database Tools for Claude AI
Allows Claude AI to interact directly with MySQL databases.
Postgres MCP
A remote MCP server for Postgres, deployable on Cloudflare Workers without authentication.