Documentation
Tutorials
Search & Research
Serper Search

Serper Search MCP

Serper (opens in a new tab) provides Google search results through a simple API, making it perfect for giving AI models access to current web information. The Serper MCP integration enables Jan models to search the web and retrieve real-time information.

Available Tools

  • google_search: Search Google and retrieve results with snippets
  • scrape: Extract content from specific web pages

Prerequisites

Serper offers 2,500 free searches upon signup - enough for extensive testing and personal use.

Setup

Enable Experimental Features

  1. Go to Settings > General
  2. Toggle Experimental Features ON

Enable experimental features

Enable MCP

  1. Go to Settings > MCP Servers
  2. Toggle Allow All MCP Tool Permission ON

Turn on MCP

Get Serper API Key

  1. Visit serper.dev (opens in a new tab)
  2. Sign up for a free account
  3. Copy your API key from the playground

Serper homepage

Serper playground with API key

Configure MCP Server

Click + in MCP Servers section:

Configuration:

  • Server Name: serper
  • Command: npx
  • Arguments: -y serper-search-scrape-mcp-server
  • Environment Variables:
    • Key: SERPER_API_KEY, Value: your-api-key

Serper MCP configuration in Jan

Download Jan v1

Jan v1 is optimized for tool calling and works excellently with Serper:

  1. Go to the Hub tab
  2. Search for Jan v1
  3. Choose your preferred quantization
  4. Click Download

Download Jan v1 from Hub

Enable Tool Calling

  1. Go to Settings > Model Providers > Llama.cpp
  2. Find Jan v1 in your models list
  3. Click the edit icon
  4. Toggle Tools ON

Enable tools for Jan v1

Usage

Start a New Chat

With Jan v1 selected, you'll see the available Serper tools:

Chat view with Serper tools

Example Queries

Current Information:


What are the latest developments in quantum computing this week?

Comparative Analysis:


What are the main differences between the Rust programming language and C++? Be spicy, hot takes are encouraged. 😌

Jan v1 using Serper for web search

Jan v1 using Serper for web search

Research Tasks:


Find the current stock price of NVIDIA and recent news about their AI chips.

Fact-Checking:


Is it true that the James Webb telescope found signs of life on an exoplanet? What's the latest?

Local Information:


What restaurants opened in San Francisco this month? Focus on Japanese cuisine.

How It Works

  1. Query Processing: Jan v1 analyzes your question and determines what to search
  2. Web Search: Calls Serper API to get Google search results
  3. Content Extraction: Can scrape specific pages for detailed information
  4. Synthesis: Combines search results into a comprehensive answer

Tips for Best Results

  • Be specific: "Tesla Model 3 2024 price Australia" works better than "Tesla price"
  • Request recent info: Add "latest", "current", or "2024/2025" to get recent results
  • Ask follow-ups: Jan v1 maintains context for deeper research
  • Combine with analysis: Ask for comparisons, summaries, or insights

Troubleshooting

No search results:

  • Verify API key is correct
  • Check remaining credits at serper.dev
  • Ensure MCP server shows as active

Tools not appearing:

  • Confirm experimental features are enabled
  • Verify tool calling is enabled for your model
  • Restart Jan after configuration changes

Poor search quality:

  • Use more specific search terms
  • Try rephrasing your question
  • Check if Serper service is operational
⚠️

Each search query consumes one API credit. Monitor usage at serper.dev dashboard.

API Limits

  • Free tier: 2,500 searches
  • Paid plans: Starting at $50/month for 50,000 searches
  • Rate limits: 100 requests per second

Next Steps

Serper MCP enables Jan v1 to access current web information, making it a powerful research assistant. Combine with other MCP tools for even more capabilities - use Serper for search, then E2B for data analysis, or Jupyter for visualization.

Exa SearchCanva