# Deepseek Mcp Server

> A small, clean MCP server for the DeepSeek API — V3 generation, chat, and R1 reasoning with visible chain-of-thought.

- **Type:** MCP server
- **Install:** `agentstack add mcp-deepzhun-deepseek-mcp-server`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [deepzhun](https://agentstack.voostack.com/s/deepzhun)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [deepzhun](https://github.com/deepzhun)
- **Source:** https://github.com/deepzhun/deepseek-mcp-server

## Install

```sh
agentstack add mcp-deepzhun-deepseek-mcp-server
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# DeepSeek MCP Server

> A small, clean [Model Context Protocol](https://modelcontextprotocol.io) server that connects any MCP client — Claude Desktop, Cursor, Cline, Cowork — to the **DeepSeek API**, including **DeepSeek-R1** reasoning with a visible chain-of-thought.

One Python file, four tools, no framework lock-in. Bring your own DeepSeek key and you get fast V3 generation, multi-turn chat, and R1 deep reasoning that shows its work — straight from your assistant.

## ✨ Tools

| Tool | What it does |
|------|--------------|
| `deepseek_generate` | Single-turn text with DeepSeek-V3 (system instruction, temperature, JSON mode) |
| `deepseek_chat` | Multi-turn conversation; switch to `deepseek-reasoner` for step-by-step thinking |
| `deepseek_reason` | Hard problems with DeepSeek-R1 — returns the reasoning trace **and** the answer |
| `deepseek_list_models` | List models available to your key |

## 🚀 Quick start

### Option A — one-click (Windows, Claude Desktop)

```powershell
# in the repo folder, right-click install.ps1 -> "Run with PowerShell"
./install.ps1
```

It asks for your API key, installs dependencies, and wires up Claude Desktop. Restart Claude and you're done.

### Option B — manual (any OS / any MCP client)

```bash
git clone https://github.com/deepzhun/deepseek-mcp-server.git
cd deepseek-mcp-server
pip install -r requirements.txt
export DEEPSEEK_API_KEY="your-api-key"     # Windows: setx DEEPSEEK_API_KEY "your-api-key"
python deepseek_mcp.py
```

Get an API key at . DeepSeek's endpoint is OpenAI-compatible.

## 🔌 Add to your MCP client

Copy `config.example.json` and drop the server block into your client config,
replacing the placeholder key:

```json
{
  "mcpServers": {
    "deepseek": {
      "command": "python",
      "args": ["/absolute/path/to/deepseek_mcp.py"],
      "env": { "DEEPSEEK_API_KEY": "YOUR_DEEPSEEK_API_KEY_HERE" }
    }
  }
}
```

## 💬 Usage examples

- "Use deepseek to draft a product update in Chinese."
- "Ask deepseek_reason to solve this logic puzzle and show its reasoning."
- "Use deepseek_chat to continue our debugging conversation."

## 🔐 Security

- The key is read from the `DEEPSEEK_API_KEY` environment variable — **never hard-code it**.
- `config.json` and `.env` are git-ignored so a real key can't be committed by accident.
- Rotate your key in the [DeepSeek console](https://platform.deepseek.com/api_keys) if it is ever exposed.

## 🛠️ Development

```bash
pip install -r requirements.txt
python -c "import deepseek_mcp; print(deepseek_mcp.mcp.name)"   # smoke test
```

Single-file server (`deepseek_mcp.py`): typed Pydantic inputs, consistent error
handling, MCP tool annotations. A sibling of [gemini-mcp-server](https://github.com/deepzhun/gemini-mcp-server) — same clean shape, different provider.

## 📄 License

MIT © deepzhun (深准). Contributions welcome — open an issue or PR.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [deepzhun](https://github.com/deepzhun)
- **Source:** [deepzhun/deepseek-mcp-server](https://github.com/deepzhun/deepseek-mcp-server)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-deepzhun-deepseek-mcp-server
- Seller: https://agentstack.voostack.com/s/deepzhun
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.