Deepseek r1

Provides a locally runnable MCP server coordinating Deepseek r1 reasoning with local models and tool calls.
  • javascript

2

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": {
    "michaelneale-deepseek-r1-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-reasoner-mcp"
      ]
    }
  }
}

You can run a locally hosted MCP server that coordinates a Deepseek r1 reasoning model with local tooling. This setup lets you perform reasoning and tool calls entirely offline, without remote models.

How to use

To use the Deepseek r1 MCP server with your MCP client, start the server and connect your client to it. The server runs locally and exposes a standard MCP interface that your client can call to perform reasoning and tool interactions.

Start the MCP server locally using the provided command. This runs the reasoning MCP server in your environment so your agent can perform local reasoning and tool calling.

npx -y deepseek-reasoner-mcp
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Deepseek r1 MCP Server - michaelneale/deepseek-r1-mcp | VeilStrat