# DeepSeek

> Use this tool when you need to integrate powerful language models with AI assistants and MCP-compatible applications, solving problems like chat completion and multi-turn conversations. DeepSeek provides a bridge between these systems, offering features like model selection, temperature control, and conversation history preservation. It is ideal for developers seeking to leverage advanced language models while maintaining anonymity through proxy access.

Canonical page: https://skillsregistry.net/skills/liuchongchong1995-deepseek  
JSON: https://api.skillsregistry.net/v1/skills/liuchongchong1995-deepseek

## Description

DeepSeek MCP Server provides a bridge between AI assistants and DeepSeek's language models through the DeepSeek API. Built with TypeScript and the Model Context Protocol SDK, it offers tools for chat completion and multi-turn conversations with support for model selection, temperature control, and other generation parameters. The server features automatic fallback from the DeepSeek Reasoner model to DeepSeek Chat when needed, maintains conversation history for context preservation, and exposes model information and configuration options through resource endpoints. It's particularly valuable for developers who want to integrate DeepSeek's powerful language models with MCP-compatible applications like Claude Desktop while maintaining anonymity through proxy access.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/liuchongchong1995-deepseek)
- **Repository:** <https://github.com/liuchongchong1995/deepseek-mcp-server>

## 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": "liuchongchong1995-deepseek"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/liuchongchong1995-deepseek` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/liuchongchong1995-deepseek/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