Skip to main content
Glama
Sign In
websearch-deepseek

websearch-deepseek

by lyumeng
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

websearch-deepseek

中文版

A universal MCP Server that provides a web search tool powered by DeepSeek's native web search API — no third-party search API required.

Works with Claude Code, Cursor, Continue, OpenCode, pi, and any tool that supports the MCP protocol.

Features

  • 🔍 DeepSeek Native Search — Uses the server-side web_search_20250305 tool, no third-party search API needed

  • 📝 AI-Generated Answers — Returns detailed answers synthesized from full page content, not just a list of URLs

  • 🔗 Source URLs Included — Every answer comes with original source links for verification

  • ⚙️ Flexible Configuration — Choose model, toggle thinking mode, adjust token limits

  • 🌐 MCP Protocol — Standard JSON-RPC over stdio, compatible with all MCP clients

Related MCP server: AIE7-MCP

How It Works

User Query → DeepSeek Model
                  ↓
        Server executes web_search (fetches pages)
                  ↓
        Encrypted page content → Server decrypts → Feeds to model
                  ↓
        Model generates detailed answer based on full content
                  ↓
Returns: AI-generated answer + source URL list

One MCP tool call = One DeepSeek API request — search, decryption, and answer generation all happen server-side.

Quick Start

1. Get a DeepSeek API Key

Visit DeepSeek Platform to sign up and get your API Key.

2. Install

npm install -g websearch-deepseek

3. Configure Your AI Coding Assistant

Add the following to your MCP configuration file:

Claude Code

Edit ~/.claude/claude_desktop_config.json or .mcp.json in your project:

{
  "mcpServers": {
    "websearch-deepseek": {
      "command": "npx",
      "args": ["websearch-deepseek"],
      "env": {
        "DEEPSEEK_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
        "WEBSEARCH_MODEL": "deepseek-v4-flash",
        "WEBSEARCH_THINKING": "enabled"
      }
    }
  }
}

Cursor

Edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "websearch-deepseek": {
      "command": "npx",
      "args": ["websearch-deepseek"],
      "env": {
        "DEEPSEEK_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Continue (VS Code)

Edit ~/.continue/config.json, add to mcpServers:

{
  "mcpServers": [
    {
      "name": "websearch-deepseek",
      "command": "npx",
      "args": ["websearch-deepseek"],
      "env": {
        "DEEPSEEK_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  ]
}

pi

Edit ~/.pi/agent/settings.json, add to mcp:

{
  "mcp": {
    "websearch-deepseek": {
      "command": "npx",
      "args": ["websearch-deepseek"],
      "env": {
        "DEEPSEEK_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

4. Start Using It

Restart your AI coding assistant and ask a question that needs real-time information. The assistant will automatically call the web_search tool when needed.

Examples:

  • "What's new in React 19?"

  • "Search for Python 3.13 release date and major updates"

  • "What are the latest AI industry news?"

Environment Variables

Variable

Required

Default

Description

DEEPSEEK_API_KEY

✅ Yes

—

DeepSeek API Key

WEBSEARCH_API_KEY

❌ No

—

Alternative API Key variable name

WEBSEARCH_MODEL

❌ No

deepseek-v4-flash

Model: deepseek-v4-flash (fast) or deepseek-v4-pro (powerful)

WEBSEARCH_THINKING

❌ No

enabled

Thinking mode: enabled / disabled

WEBSEARCH_MAX_TOKENS

❌ No

8192

Max tokens for response

Model Selection Guide

Scenario

Recommended Model

Notes

Daily search (default)

deepseek-v4-flash

Fast, low cost, good quality

Deep research

deepseek-v4-pro

More detailed and accurate, slightly slower

Thinking Mode

  • enabled (default): The model thinks before answering, producing higher quality results but consuming more tokens

  • disabled: Skips the thinking step for faster responses, suitable for simple queries

CLI Usage

You can also use it directly from the terminal:

# Set API Key
export DEEPSEEK_API_KEY=sk-xxxxxxxxxxxxxxxx

# Search
npx websearch-deepseek search "Node.js LTS versions"

# JSON output
npx websearch-deepseek search --json "TypeScript 5.8"

# Specify model and disable thinking
npx websearch-deepseek search --model deepseek-v4-pro --no-thinking "Rust latest version"

Output Example

## Node.js Latest LTS Versions

As of July 2025, the latest Active LTS version of Node.js is Node.js 24.x...

| Version | Status | Initial Release | Support Until |
|---------|--------|-----------------|---------------|
| 24.x    | Active LTS | 2025-05-06 | 2028-04 |
| 22.x    | Maintenance | 2024-10   | 2027-04 |

### Recommendations
- New projects: Use Node.js 24 LTS
- Existing projects: Node.js 22 continues to receive security updates

---

### Sources (10):
1. [Node.js 24.0 is available...](https://...)
2. [Node.js — Node.js Releases](https://...)
...

Pricing

This tool uses the DeepSeek API, which charges per token. A single search typically consumes:

Component

Estimated Tokens

Search + thinking

~5,000–8,000

Generate answer

~1,000–3,000

Total per search

~8,000–15,000 tokens

Check DeepSeek pricing for current rates.

License

MIT

Available Tools

1 tool
web_searchA

搜索互联网获取当前、实时或事实性信息。 当你需要训练数据之外的信息时使用此工具—— 近期事件、当前数据、文档查询或事实核查。 返回基于完整网页内容生成的 AI 详细回答，附带来源 URL。 由 DeepSeek 原生联网搜索 API 驱动（服务端执行）。

English: Search the web for current, real-time, or factual information. Use this tool when you need information beyond your training cutoff — recent events, current data, documentation lookups, or fact-checking. Returns a detailed AI-generated answer based on full page content, plus source URLs. Powered by DeepSeek's native web search API.

Inputs: query (required), explanation.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.7/5.0

    Scored across 1 tool

    Disambiguation5/5

    Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly defined as web search.

    Naming Consistency5/5

    The single tool name 'web_search' follows a clear verb_noun pattern and accurately reflects its function. No mixed conventions or vague naming.

    Tool Count5/5

    The server's purpose is exclusively web search, and a single tool fully satisfies that purpose. The count is neither excessive nor insufficient for the stated scope.

    Completeness5/5

    The web search tool covers the entire domain of the server, providing access to current information, real-time data, and factual verification. There are no apparent gaps for this narrow purpose.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • evo-scry

      krich11
      A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.
      MIT

    • deepseek-search-mcp

      zouyuanqing
      A
      license
      A
      quality
      D
      maintenance
      A DeepSeek-powered MCP server that provides high-accuracy web search using the native DeepSeek V4-Flash search API, offering standard and deep research tools that return cited answers and cross-verified reports.
      4
      1
      MIT

    • websearch-deepseek

      applex250
      A
      license
      A
      quality
      D
      maintenance
      An MCP server that provides web search powered by DeepSeek's native search API, returning AI-generated answers with source links. Integrates with MCP-compatible clients like Claude Code and Cursor.
      1
      MIT