MCP LLM Server

An MCP server that provides LLMs access to other LLMs

javascript

77

GitHub Stars

javascript

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": {
    "sammcj-mcp-llm": {
      "command": "node",
      "args": [
        "examples/use-mcp-server.js"
      ]
    }
  }
}

You can run an MCP server that exposes LLM-powered tools and interact with it from your client applications. This server lets you generate code, create documentation, and ask questions to an LLM, streamlining your development workflow and enabling automation via simple calls from your own tools.

How to use

Start by running the provided server script. This MCP server starts and then you can interact with it from your client using standard HTTP or JSON-RPC approaches, or by using the local runtime via the example script. The example script demonstrates how to spin up the server and send requests to it using curl commands.

How to install

Prerequisites: you need Node.js and npm installed on your system. You may also use npx for quick client-side commands.

Step 1: Install dependencies and build the project from source.

# Optional: install via Smithery for streamlined setup
npx -y @smithery/cli install @sammcj/mcp-llm --client claude

# Manual install from source
git clone https://example.org/placeholder/mcp-llm.git
cd mcp-llm
npm install
npm run build

Additional notes

Using the example script is a practical way to learn how to interact with the MCP server. Run the script to start the server, then send requests with curl to exercise the available tools.

Example tool usage you can perform once the server is running includes generating code based on a description, generating code written to a specific file and line, generating documentation for code, and asking questions to the LLM.

Example tool usage and data formats

Generate Code example description: Create a function that calculates the factorial of a number. Language: JavaScript.

Generate Code to File example description: Create a function that calculates the factorial of a number. Language: JavaScript. File path: /path/to/factorial.js. Line number: 10. Replace lines: 0.

Generate Documentation example: Code snippet for a factorial function in JavaScript with JSDoc format.

Ask Question example: What is the difference between var, let, and const in JavaScript? Context: I’m a beginner learning JavaScript and confused about variable declarations.

Available tools

generate_code

Generates code based on a descriptive prompt for a target language.

generate_code_to_file

Generates code and writes it directly to a specified file at a given line number.

generate_documentation

Generates documentation for the provided code snippet.

ask_question

Sends a natural language question to the LLM and returns an answer.