Skip to content
Back to search

library-mcp

MCP server for operating on Markdown knowledge bases

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/lethain--library-mcp/badge.svg)](/listings/lethain--library-mcp)

HTML

<a href="/listings/lethain--library-mcp"><img src="/api/listings/lethain--library-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These instructions describe installation for [Claude Desktop](https://claude.ai/download) on OS X. It should work similarly on other platforms.

1. Install [Claude Desktop](https://claude.ai/download). 2. Clone [library-mcp](https://github.com/lethain/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](https://modelcontextprotocol.io/quickstart/server) 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...

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 107 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. [library-mcp](https://github.com/lethain/library-mcp) is an MCP server for interacting with
  2. Markdown knowledge bases. Basically, folders that may or may not have subfolders, that include
  3. files with `.md` extension and start with metadata like:
  4. ----
  5. title: My blog post
  6. tags:
  7. - python
  8. - programming
  9. url: /my-blog-post
  10. ---
  11. # My blog post
  12. Yesterday I was dreaming about...
  13. The typical workflow in the current verison is to
  14. retrieve recent content for a given tag, and then
  15. discuss using that tag:
  16. Get the next 50 posts with tag "executive",
  17. then tell me what I should do about this problem
  18. I am running into: ...
  19. You can also do the same but by date ranges:
  20. Summarize the blog posts I wrote in the past year.
  21. You might reasonably ask "why not just upload your entire blog
  22. into the context window?" and there are two places where this library
  23. outperforms that approach:
  24. 1. My blog corpus is much larger than most model's context windows today.
  25. Further, even if the context windows became exhaustively large, I wrote a lot
  26. of mediocre stuff in the past, so maybe omitting it's a feature.
  27. 2. I have a number of distinct Markdown knowledge bases, and this lets me
  28. operate across them in tandem.
  29. Finally, this is a hobby project, intended for running locally on your
  30. laptop. No humans have been harmed using this software, but it does
  31. work pretty well!
  32. # Tools
  33. This MCP server exposes these tools.
  34. ### Content Search Tools
  35. Tools for retrieving content into your context window:
  36. * `get_by_tag` - Retrieves content by tag
  37. * `get_by_text` - Searches content for specific text
  38. * `get_by_slug_or_url` - Finds posts by slug or URL
  39. * `get_by_date_range` - Gets posts published within a date range
  40. ### Tag Management Tools
  41. Tools for navigating your knowledge base:
  42. * `search_tags` - Searches for tags matching a query
  43. * `list_all_tags` - Lists all tags sorted by post count and recency
  44. ### Maintenance Tools
  45. Tools for dealing with running the tool:
  46. * `rebuild` - Rebuilds the content index,
  47. useful if you have added more content,
  48. edited existing content, etc
  49. # Setup / Installation
  50. These instructions describe installation for [Claude Desktop](https://claude.ai/download) on OS X.
  51. It should work similarly on other platforms.
  52. 1. Install [Claude Desktop](https://claude.ai/download).
  53. 2. Clone [library-mcp](https://github.com/lethain/library-mcp) into
  54. a convenient location, I'm assuming `/Users/will/library-mcp`
  55. 3. Make sure you have `uv` installed, you can [follow these instructions](https://modelcontextprotocol.io/quickstart/server)
  56. 4. Go to Cladue Desktop, Setting, Developer, and have it create your MCP config file.
  57. Then you want to update your `claude_desktop_config.json`.
  58. (Note that you should replace `will` with your user, e.g. the output of `whoami`.
  59. cd /Users/will/Library/Application Support/Claude
  60. vi claude_desktop_config.json
  61. Then add this section:
  62. {
  63. "mcpServers": {
  64. "library": {
  65. "command": "uv",
  66. "args": [
  67. "--directory",
  68. "/Users/will/library-mcp",
  69. "run",
  70. "main.py",
  71. "/Users/will/irrational_hugo/content"
  72. ]
  73. }
  74. }
  75. }
  76. 5. Close Claude and reopen it.
  77. 6. It should work...

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.