Grok MCP
Reach xAI's Grok models from your own client — chat, vision, web and X search, code execution, image and video generation.Read full description
merterbakLABSCO SUMMARY
A second opinion from a different model, inside the same conversation.
The shape is simple — your assistant recognises a query that needs deeper reasoning, sends it out, and gets back the working rather than a verdict, which keeps the final answer in the model you were already talking to. It needs a paid DeepSeek key and a local clone, so it is a deliberate addition rather than something to leave running by default.
What it is
A small Python MCP server that forwards a query to DeepSeek's R1 reasoning model and returns the structured reasoning, so the assistant you are already talking to can fold it into its own answer.
What you get
- A reasoning step delegated to DeepSeek R1 without leaving the conversation
- Structured reasoning returned to the client, rather than a finished answer that replaces yours
- Support for multi-step problems, where the reasoning is worth seeing separately from the response
Requirements
Python 3.12 or higher, the uv package manager, and a DeepSeek API key from the DeepSeek platform. Clone the repository, create the environment, paste your key into server.py, and point your client at the server script.
Setup effort
Build from source — git clone https://github.com/HarshJ23/deepseek-claude-MCP-server.git
USE CASES
01
Getting a second model to check a multi-step argument
Send the problem out for reasoning and compare it against what your assistant already concluded.
02
Seeing the working, not just the answer
Pull back the structured reasoning so you can find the step you disagree with.
03
Handling a problem your assistant keeps getting wrong
Delegate the reasoning stage and let your assistant write the final response from it.
BEFORE YOU INSTALL
What to know first
Requires
- Python 3.12 or higher
- uv package manager
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/HarshJ23/deepseek-claude-MCP-server.git
cd deepseek-claude-MCP-server
uv venv
source .venv/bin/activate
uv add "mcp[cli]" httpxOpen server.py and set DEEPSEEK_API_KEY (it reads "enter your api key") to your key from https://platform.deepseek.com/api_keys — the server reads the key from that line, not from the environment.
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"deepseek-claude": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_DEEPSEEK_CLAUDE_MCP_SERVER>",
"run",
"server.py"
]
}
}
}
