# DeepSeek Thinker

> Use this tool when you need to generate chain-of-thought reasoning and perform complex problem-solving tasks, such as multi-step reasoning, decision-making support, and in-depth analysis. It provides a standardized interface for interacting with the DeepSeek Thinker model, accepting inputs and producing outputs that enable AI models to tackle sophisticated scenarios. Ideal for applications like research assistance, strategic planning, and complex data interpretation, this tool leverages advanced cognitive abilities to drive AI-driven problem-solving.

Canonical page: https://skillsregistry.net/skills/ruixingshi-deepseek-thinker  
JSON: https://api.skillsregistry.net/v1/skills/ruixingshi-deepseek-thinker

## Description

This MCP server, developed by Ruixing Shi, provides a standardized interface for interacting with the DeepSeek Thinker model. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers tools for generating chain-of-thought reasoning. The implementation focuses on exposing DeepSeek's advanced reasoning capabilities through a consistent MCP interface, enabling AI models to perform complex problem-solving and analytical tasks. By connecting AI assistants with DeepSeek's powerful cognitive abilities, this server facilitates sophisticated scenarios like multi-step reasoning, decision-making support, and in-depth analysis. It's particularly valuable for applications requiring advanced AI-driven problem-solving, such as research assistance, strategic planning, and complex data interpretation.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ruixingshi-deepseek-thinker)
- **Repository:** <https://github.com/ruixingshi/deepseek-thinker-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ruixingshi-deepseek-thinker"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ruixingshi-deepseek-thinker` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ruixingshi-deepseek-thinker/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt