Skip to main content
Glama
hbhszy

web-search-mcp

by hbhszy

web-search-mcp

An online search MCP server based on the DeepSeek web version. It provides real-time web search capabilities to MCP clients through DeepSeek's search-enhanced dialogue feature.

Features

  • Provides the web_search MCP tool, supporting real-time web search

  • Supports DeepSeek default and expert models

  • Supports thinking process output

  • Zero dependencies, pure Node.js implementation

  • stdio transport, compatible with all MCP clients

Related MCP server: google-search-mcp

Quick Start

1. Use in Claude Desktop

Edit the Claude Desktop configuration file (claude_desktop_config.json) and pass credentials directly via the env field, no .env file required:

{
  "mcpServers": {
    "web-search": {
      "command": "node",
      "args": ["D:/ai-projects/web-search-mcp/src/index.js"],
      "env": {
        "DEEPSEEK_AUTH_TOKEN": "your_token_here"
      }
    }
  }
}

2. Use in Claude Code

Add the following to your project's .claude/settings.json:

{
  "mcpServers": {
    "web-search": {
      "command": "node",
      "args": ["D:/ai-projects/web-search-mcp/src/index.js"],
      "env": {
        "DEEPSEEK_AUTH_TOKEN": "your_token_here"
      }
    }
  }
}

3. Use a .env file (Optional)

If it is inconvenient to write env in the MCP configuration, you can also use a .env file:

cp .env.example .env
# 编辑 .env 填入凭据

Environment variable priority: System environment variables > MCP env configuration > .env file

MCP Tools

Uses DeepSeek's search-enhanced dialogue to perform a web search and returns an answer based on the search results.

Parameters:

Parameter

Type

Required

Description

query

string

Yes

Search query content

thinking

boolean

No

Whether to enable DeepSeek thinking/reasoning mode. If enabled, the model will reason before answering, and the reasoning process is included in the response (default: false)

model

string

No

Model mode: default or expert (defaults to configuration value)

Environment Variables

Variable

Required

Default

Description

DEEPSEEK_AUTH_TOKEN

One of two

-

DeepSeek login token

DEEPSEEK_COOKIE

One of two

-

DeepSeek browser cookie

DEEPSEEK_MODEL_TYPE

No

default

Model type: default or expert

DEEPSEEK_THINKING_ENABLED

No

false

Whether to enable the thinking process by default

WASM_PATH

No

assets/sha3_wasm_bg...wasm

Path to the PoW solver WASM file

LOG_LEVEL

No

info

Log level: debug, info, error

Obtaining DeepSeek Credentials

  1. Open chat.deepseek.com and log in

  2. Open browser developer tools (F12) → switch to the Console panel

  3. Enter the following command and press Enter to copy the token:

copy(JSON.parse(localStorage.getItem("userToken")).value)
  1. Paste it into the DEEPSEEK_AUTH_TOKEN environment variable

Note: Credentials will expire and need to be re-obtained. A typical sign of token expiration is the request returning a Cloudflare verification page.

Testing

# 运行所有测试
npm test

# 运行单个测试文件
node --test tests/mcp-protocol.test.js
node --test tests/config.test.js

Project Structure

src/
  index.js            # 入口,初始化所有组件并启动 MCP 服务器
  mcp-server.js       # MCP 协议处理(stdio 传输、JSON-RPC 分发)
  deepseek-client.js  # DeepSeek 网页版 API 客户端(会话管理、PoW、SSE 流式解析)
  pow-solver.js       # SHA3 PoW WASM 求解器
  env.js              # .env 文件加载器
  config.js           # 环境变量配置解析
Install Server
A
license - permissive license
A
quality
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • The best web search for your AI Agent

  • Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.

  • LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hbhszy/web-search-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server