Memex

Provides a Memex MCP server that analyzes web content and stores a Markdown knowledge base for model context.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "narphorium-mcp-memex": {
      "command": "uv",
      "args": [
        "--directory",
        "PATH_TO_LOCAL_MEMEX_REPO",
        "run",
        "mcp-memex",
        "--index",
        "PATH_TO_MEMEX_INDEX",
        "--workspace",
        "PATH_TO_OBSIDIAN_VAULT"
      ],
      "env": {
        "VOYAGE_API_KEY": "YOUR-API-KEY",
        "ANTHROPIC_API_KEY": "YOUR-API-KEY",
        "FIRECRAWL_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Memex MCP Server lets you analyze web content and add it to your knowledge base, enabling your models to reason with richer context drawn from online sources. It stores results as Markdown files for easy viewing in any Markdown viewer (Obsidian is recommended).

How to use

You interact with Memex MCP through an MCP client. Start by configuring and launching the Memex MCP server, then ask your client a question accompanied by the URLs you want analyzed. Memex will process the pages and save a Markdown knowledge base in your workspace. Open your Obsidian vault (or Markdown viewer) to explore the results, and you can ask follow-up questions to refine or expand the context based on the indexed content.

How to install

Prerequisites you need before starting:

Python 3.x and pip installed on your machine.
Node.js and npm for running the inspector tool.

Follow these steps to install and run Memex MCP Server:

pip install mcp-memex

{
  "mcpServers": {
    "memex": {
      "command": "uv",
      "args": [
        "--directory",
        "PATH_TO_LOCAL_MEMEX_REPO",
        "run",
        "mcp-memex",
        "--index",
        "PATH_TO_MEMEX_INDEX",
        "--workspace",
        "PATH_TO_OBSIDIAN_VAULT"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "YOUR-API-KEY",
        "FIRECRAWL_API_KEY": "YOUR-API-KEY",
        "VOYAGE_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Additional steps and notes

Configure your client to point to the Memex MCP server and supply the URLs you want analyzed. The Memex tool will analyze the provided web content, store the results as Markdown in your workspace, and you can query the knowledge base later as needed.

To run the inspector locally and connect to the Memex server, use the development command shown below. This starts the UI and connects to the Memex MCP instance.

npx @modelcontextprotocol/inspector \
  uv \
  --directory PATH_TO_LOCAL_MEMEX_REPO \
  run \
  mcp-memex \
  --index PATH_TO_MEMEX_INDEX \
  --workspace PATH_TO_OBSIDIAN_VAULT

Then open http://localhost:5173?timeout=30000 in your browser to access the inspector UI.

Built by

VeilStrat

AI signals for GTM teams