mcpField
G
groq-compound-mcp-server

groq-compound-mcp-server

Local
github.com/groqAI & Agents56Updated 10w ago
Repository

About groq-compound-mcp-server

groq-compound-mcp-server is an MCP server for calling Groq compound and meta models. It is aimed at developers who want real-time information lookup or code execution available inside MCP clients.

Key features

  1. 01Real-time information tool ask_with_realtime_information
  2. 02Code execution tool ask_with_code_execution
  3. 03Runs over stdio transport
  4. 04Requires GROQ_API_KEY environment variable
  5. 05Can be deployed to Vercel with SSE transport

Use cases

  1. 01Letting a model answer questions with up-to-date information in Claude Desktop
  2. 02Running code through a model and returning the results
  3. 03Hosting Groq models as an MCP service on Vercel

MCP support

This is an MCP server that exposes the ask_with_realtime_information and ask_with_code_execution tools to MCP clients.

#managed-by-terraform

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "compound": {
      "command": "npx",
      "args": [
        "-y",
        "groq-compound-mcp-server"
      ],
      "env": {
        "GROQ_API_KEY": "<GROQ_API_KEY>"
      }
    }
  }
}
Run commandnpx -y groq-compound-mcp-server
Environment variables to set
GROQ_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmgroq-compound-mcp-server

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
questionstringYesThe question to ask the model, especially if it requires real-time information (e.g., current news, recent events).
modelenumNoThe model to use (compound-beta or compound-beta-mini). Defaults to compound-beta. Use compound-beta-mini for quick answers.compound-beta | compound-beta-mini
modeenumNoResponse mode ('minimal' or 'verbose'). Defaults to 'minimal'. 'verbose' includes executed tools in the response. This is very verbose and should only be used when the user asks for it or when the user query cannot be answered without it (always first try without it).minimal | verbose
include_domainsarrayNoList of domains to specifically include in the search.
exclude_domainsarrayNoList of domains to exclude from the search.

Details

From the project README

groq-compound-mcp-server

Provides a Model Context Protocol (MCP) server for interacting with Groq models, including compound/meta models.

This server exposes the following tools:

  • ask_with_realtime_information
  • ask_with_code_execution

Prerequisites

  • Node.js >= 18.0.0
  • A Groq API key set in the GROQ_API_KEY environment variable.

Installation

npm install groq-compound-mcp-server

Usage

This server follows the standard MCP server pattern using stdio for transport. It's designed to be run by an MCP client (like Claude Desktop or a custom client).

Refer to the official MCP Quickstart for Server Developers for instructions on setting up and connecting MCP servers.

When configuring your client, use the command npx groq-compound-mcp-server or groq-compound-mcp-server (if installed globally) to run this server.

Here's an example of how you might configure an MCP client (e.g., in a settings.json file) to launch this server:

{
  "mcpServers": {
    "groq-compound": {
      "command": "npx",
      "args": [
        "-y",
        "groq-compound-mcp-server"
      ],
      "env": {
        "GROQ_API_KEY": "YOUR_GROQ_API_KEY_HERE"
      }
    }
  }
}

Hosting on Vercel

This server can also be deployed to Vercel.

  1. Prerequisites:

    • Ensure you have a Vercel account.
    • Connect your Git repository to Vercel.

  2. Environment Variables: Set the following environment variables in your Vercel project settings:

    • GROQ_API_KEY: Your Groq API key.
    • REDIS_URL: (Recommended for SSE transport) The connection URL for a Redis instance (e.g., from Vercel KV or Upstash).

  3. Build Configuration: Vercel should automatically detect it as a Next.js application. The build command npm run build:vercel (or yarn build:vercel/pnpm build:vercel) and the output directory (.next) will be used.

  4. Accessing the MCP Server: Once deployed, your MCP server endpoints will be available at https://your-deployment-url.vercel.app/api/mcp. For example, the SSE endpoint would be https://your-deployment-url.vercel.app/api/mcp/sse.

Development with Vercel CLI

To run the Vercel deployment locally:

  1. Install Vercel CLI: npm install -g vercel
  2. Set up environment variables locally (e.g., in a .env.local file at the project root): 
    GROQ_API_KEY=your_groq_api_key
REDIS_URL=your_redis_url
  3. Run the development server: vercel dev or npm run dev:vercel.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.