Skip to main content
Glama
aimmetal-tech

deepseek-search-mcp

README.md
# deepseek-search-mcp

[![DeepSeek](https://img.shields.io/badge/DeepSeek-Search_API-4D6BFE?logo=deepseek&logoColor=white)](https://api-docs.deepseek.com/guides/search/)
[![MCP](https://img.shields.io/badge/MCP-Model_Context_Protocol-000000?logo=modelcontextprotocol&logoColor=white)](https://modelcontextprotocol.io)
[![TypeScript](https://img.shields.io/badge/TypeScript-7-3178C6?logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)

一个基于 [DeepSeek Search API](https://api-docs.deepseek.com/guides/search/) 的 MCP(Model Context Protocol)服务器,通过 stdio 为 AI Agent 提供实时网页搜索与网页抓取能力。

## 工具

| 工具     | 说明                                         | 参数                                                        |
| -------- | -------------------------------------------- | ----------------------------------------------------------- |
| `search` | 搜索网页,返回标题、链接、摘要、正文等内容   | `query`:搜索关键词                                         |
| `fetch`  | 抓取网页,返回页面标题与 Markdown 格式的内容 | `url`:`https://` 或 `http://` 开头的链接(最长 8192 字符) |

## 安装

需要 Node.js 20+ 和一个 [DeepSeek API Key](https://platform.deepseek.com/)。

在 MCP 客户端(如 VS Code、Claude Desktop 等)的配置文件中添加:

```json
{
    "servers": {
        "deepseek-search": {
            "type": "stdio",
            "command": "npx",
            "args": ["-y", "github:aimmetal-tech/deepseek-search-mcp"],
            "env": { "DS_API_KEY": "sk-xxxx" }
        }
    }
}
```

把 `sk-xxxx` 替换为你自己的 API Key。`npx` 会自动克隆仓库、安装依赖并构建,无需手动操作。

### 本地开发

```bash
git clone https://github.com/aimmetal-tech/deepseek-search-mcp.git
cd deepseek-search-mcp
npm install
cp .env.example .env   # 填入 DS_API_KEY
npm run dev
```

## API 文档

本项目基于 DeepSeek 官方的 Search 与 Fetch 接口:

- [Search API — `POST /v1/tools/search`](https://api-docs.deepseek.com/guides/search/)
- [Fetch API — `POST /v1/tools/fetch`](https://api-docs.deepseek.com/guides/search/)

## License

[MIT](./LICENSE)

TDQS

B3.2/5.0

Scored across 2 tools

Disambiguation5/5

search and fetch have clearly distinct purposes: one locates web results, the other retrieves a specific page's content. There is no meaningful overlap in how an agent would select between them.

Naming Consistency4/5

Both names are lowercase single verbs, which is consistent and readable. However, there is no object/noun component to make the pattern as predictable as a verb_noun convention.

Tool Count4/5

Two tools is slightly thin, but this server has a narrowly scoped search-and-fetch purpose where each tool clearly earns its place. It is not excessive or confusing.

Completeness4/5

The core lifecycle of web search followed by page retrieval is covered. Minor gaps exist, such as filtering, pagination, or batch retrieval, but agents can still accomplish the main use cases.

Maintenance

ActivityMaintained
ResponsivenessNo issues