A
licenseNot graded
qualityD
maintenanceMCP 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
websearch-deepseek
by lyumeng
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@websearch-deepseekWhat are the latest features of React 19?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
websearch-deepseek
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_20250305tool, 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 listOne 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-deepseek3. 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 |
| ✅ Yes | — | DeepSeek API Key |
| ❌ No | — | Alternative API Key variable name |
| ❌ No |
| Model: |
| ❌ No |
| Thinking mode: |
| ❌ No |
| Max tokens for response |
Model Selection Guide
Scenario | Recommended Model | Notes |
Daily search (default) |
| Fast, low cost, good quality |
Deep research |
| 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 toolweb_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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 搜索关键词。请具体并包含相关关键词以获得更好结果。 / The search query. Be specific and include relevant keywords. | |
| explanation | No | 一句话解释为什么需要搜索，帮助理解上下文。 / One sentence explaining why this search is needed. |
TDQS
A4.6/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns an AI-generated answer based on full page content plus source URLs, and notes it is powered by DeepSeek's native web search API with server-side execution. This adds valuable behavioral context about output format and implementation. It doesn't mention potential limitations like rate limits or latency, but for a search tool this is reasonably transparent. A 4 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately sized, provided bilingually, and well-structured with a clear separation of purpose, usage, and output. Every sentence contributes value, but the bilingual repetition (Chinese and English) makes it slightly longer than strictly necessary. Still, each part earns its place, so it is concise for a description that needs to serve both languages.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with only two parameters (one required) and no output schema, the description provides complete context: what it does, when to use it, what it returns (detailed AI answer + source URLs), and a hint for parameter usage. There is no ambiguity about the tool's operation or expected results, making it fully self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers both parameters with descriptions (100% coverage). The description adds extra guidance for the query parameter, advising the user to be specific and include relevant keywords. This goes beyond the schema by offering a practical tip for better results, which is helpful for an agent crafting effective search queries.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches the internet for current, real-time, or factual information, with a specific verb ('search') and resource ('the web'). It goes beyond a simple statement by listing concrete use cases (recent events, current data, documentation lookups, fact-checking), making the tool's purpose unmistakable even without sibling tools to compare against.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to use this tool when information is needed beyond the training cutoff, and lists specific scenarios: recent events, current data, documentation lookups, or fact-checking. This gives clear when-to-use guidance, and the implicit contrast with 'training data' tells the agent when not to use it (for general knowledge already known).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
A4.7/5.0
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.
Maintenance
ActivityStale
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Serper MCP — wraps the Serper Google Search API (serper.dev)
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Related MCP Servers
- FlicenseAqualityDmaintenanceMCP server that provides web search capabilities using the Tavily API.3
- AlicenseAqualityBmaintenanceA 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.41MIT
- AlicenseAqualityCmaintenanceAn 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.1MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/lyumeng/websearch-deepseek'
If you have feedback or need assistance with the MCP directory API, please join our Discord server