Groq Mcp Client
About
A free MCP client server that leverages GroqCloud's high-performance inference capabilities and connects to both local and remote MCP servers.
Details
- Author
- YeshwanthSadum
- Downloads
- 304
- Categories
- Other
Jump to
- CLI chat interface for MCP servers
- Supports both stdio and SSE server transports
- Uses Groq’s API for model inference
- Configurable model via CLIENT_MODEL environment variable
- Works with local and public MCP servers
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Groq Mcp ClientCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, create a virtual environment (recommended with uv), install dependencies via uv pip install -e ., then add a .env file with your GROQ_API_KEY and CLIENT_MODEL. Configure the MCP servers in server_config.json (list local scripts under "stdio_servers" and remote SSE endpoints under "sse_servers"). Finally, run python src/main.py to start the interactive chat.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"groq mcp client": {
"groq-mcp-client": {
"command": "uv",
"args": [
"venv",
"#",
"Creates",
".venv",
"directory"
]
}
}
}
}McpServers
{
"groq-mcp-client": {
"command": "uv",
"args": [
"venv",
"#",
"Creates",
".venv",
"directory"
]
}
}Installation
1. Clone the repository:
git clone <repository-url>
cd groqcloud-mcp-client
2. Create virtual environment and activate it:
uv venv # Creates .venv directory
source .venv/bin/activate # Linux/Mac
# or .\.venv\Scripts\activate on Windows
If you don't have uv, you can follow these steps and install it.
4. Install dependencies (uv will read from pyproject.toml and uv.lock):
uv pip install -e . # For editable install
# or
uv pip install . # For regular install
5. Add .env file:
GROQ_API_KEY='gsk_**'
CLIENT_MODEL='deepseek-r1-distill-llama-70b'
You can obtain the GROQ_API_KEY from https://console.groq.com/keys after you login.
Usage
1. activate venv:
source .venv/bin/activate
3. Update the server_config.json with required MCP servers.
Example:
{
"stdio_servers": [
"/home/dell/Documents/mcp/weather/weather.py"
],
"sse_servers": [
"https://btc.maratech.com/",
"https://insurancemcpserver.up.railway.app/"
]
}
- stdio_servers are the servers that are available locally. Leave the list empty if you
don't have any. You can follow the
MCP server docs to create a
local MCP server
- Explore active SSE servers registered at https://ui.nanda-registry.com/explorer
2. Run the CLI chat tool:
python src/main.py
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
