LLM Wiki MCP Server

by flsteven87 Your server? Claim it

local only

LLM Wiki MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 160 installs a week from pypi. Last commit 8 Apr 2026.

MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.

Installs per day peak 32 · avg 19 · +45% w/w

a month agotoday

160

Installs / week

pypi · llm-wiki-mcp

Stars

0 open issues

8 Apr 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check LLM Wiki MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add llm-wiki-mcp -- uvx llm-wiki-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "llm-wiki-mcp": {
      "command": "uvx",
      "args": [
        "llm-wiki-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.llm-wiki-mcp]
command = "uvx"
args = ["llm-wiki-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "llm-wiki-mcp": {
      "command": "uvx",
      "args": [
        "llm-wiki-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "llm-wiki-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "llm-wiki-mcp"
      ]
    }
  }
}

Alternatives to LLM Wiki MCP

same job, measured the same way

gknowledge

by openapi

Search, read and grow a Karpathy-style LLM wiki of linked Markdown pages, with cited answers.

147 installs/wk local only

Agent Wiki

by getagentwiki

Hosted markdown project wikis your team's AI assistants read, search, and update over MCP.

answering

DuDuClaw

by zhixuli0406

Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.

1 458 installs/wk local only

gosidian

by daniele-chiappa

Self-hosted Obsidian-compatible markdown vault with a web UI and a 71-tool MCP server for AI agents

local only

Enquire MCP

by oomkapwn

Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.

993 installs/wk local only

Nix

by paulocesaaars

Servidor MCP stdio para wikis em Markdown

local only

Factsets MCP Server

by joshua-auchincloss

An MCP server that provides a local, persistent, self-maintaining knowledge base for AI agents

110 installs/wk local only

mwe-mcp — Memory Wiki Engine

by fr4nz82

Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.

local only

LLM Wiki MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for LLM Wiki MCP?

LLM Wiki MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package llm-wiki-mcp was installed 160 times last week.

How do I connect LLM Wiki MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls llm-wiki-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use LLM Wiki MCP?

The pypi package llm-wiki-mcp was installed 160 times in the last week. Week over week that is +45%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is LLM Wiki MCP open source?

Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.