MCP LLMs Txt

MCP server for SecretiveShell/Awesome-llms-txt. Add documentation directly into your conversation via MCP resources.

python

24

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": {
    "secretiveshell-mcp-llms-txt": {
      "command": "uvx",
      "args": [
        "mcp-llms-txt"
      ],
      "env": {
        "PYTHONUTF8": "1"
      }
    }
  }
}

You set up an MCP server for Awesome-llms-txt to inject and access in-conversation documentation via MCP resources. This lets you extend your chat with structured data and endpoints that your client can request on demand.

How to use

When you run the MCP server, you connect using an MCP client. The server exposes resources you can reference in your conversations to pull documentation or structured data into chat sessions. Use the client to request the server for relevant content during a session, and the server will respond with the appropriate documentation blocks, examples, or explanations based on your prompts.

How to install

Prerequisites: you need Node.js and npm (or npx) installed on your machine. You also need Python 3 to ensure UTF-8 handling if your environment relies on Python configurations.

Option A — Install via Smithery (automatic setup) with Claude Client:

npx -y @smithery/cli install @SecretiveShell/MCP-llms-txt --client claude

Option B — Manual configuration (local client, example config):

{
  "mcpServers": {
    "mcp_llms_txt": {
      "command": "uvx",
      "args": ["mcp-llms-txt"],
      "env": {
        "PYTHONUTF8": "1"
      }
    }
  }
}

Additional steps

After you configure the MCP server, you can test it with the MCP CLI to ensure it responds correctly. The test runs your configured MCP setup using a local JSON config.

Testing command to run in your project directory:

npx -y "@wong2/mcp-cli" -c config.json