Skip to main content
Glama
websearch-deepseek

websearch-deepseek

by applex250

websearch-deepseek

ไธญๆ–‡็‰ˆ

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

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

Features

  • ๐Ÿ” DeepSeek Native Search โ€” Uses the server-side web_search_20250305 tool, no third-party search API needed

  • ๐Ÿ“ AI-Generated Answers โ€” Returns detailed answers synthesized from full page content, not just a list of URLs

  • ๐Ÿ”— Source URLs Included โ€” Every answer comes with original source links for verification

  • โš™๏ธ Flexible Configuration โ€” Choose model, toggle thinking mode, adjust token limits

  • ๐ŸŒ MCP Protocol โ€” Standard JSON-RPC over stdio, compatible with all MCP clients

Related MCP server: websearch-deepseek

How It Works

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

One MCP tool call = One DeepSeek API request โ€” 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

โœ… Yes

โ€”

DeepSeek API Key

WEBSEARCH_API_KEY

โŒ No

โ€”

Alternative API Key variable name

WEBSEARCH_MODEL

โŒ No

deepseek-v4-flash

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

WEBSEARCH_THINKING

โŒ No

enabled

Thinking mode: enabled / disabled

WEBSEARCH_MAX_TOKENS

โŒ 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 โ€” 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

~5,000โ€“8,000

Generate answer

~1,000โ€“3,000

Total per search

~8,000โ€“15,000 tokens

Check DeepSeek pricing for current rates.

License

MIT


Available Tools

1 tool

Tool Schema Changelog

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

Loading tool schema changelogโ€ฆ

    TDQS

    A4.6/5.0

    Scored across 1 tool

    Disambiguation5/5

    Only one tool exists, so there is no possibility of confusion between overlapping purposes. The tool's purpose is clear and unambiguous.

    Naming Consistency5/5

    The single tool name 'web_search' follows a clear verb_noun pattern, which is consistent and descriptive. No naming conflicts or mixed conventions exist.

    Tool Count5/5

    One tool is perfectly scoped for a web search server; additional tools would be redundant. The tool fully embodies the server's purpose without unnecessary bloat or thinness.

    Completeness5/5

    For a web search domain, the tool covers the complete expected functionality: fetching current, real-time, and factual information with sources. There are no obvious gaps or missing operations.

    Related MCP Connectors

    Related MCP Servers