Web Search Tool
Allows searching the web via Google Search API through Serper.dev, returning results with titles, links, snippets, and a summary answer.
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., "@Web Search Toolsearch the web for Claude MCP integration tips"
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.
๐ MCP Server: Web Search Tool (FastMCP + Serper)
A lightweight, Claude-ready MCP (Model Context Protocol) server that wraps the Serper.dev Google Search API using Python, LangChain, and FastMCP.
This server exposes a structured, LLM-callable tool that performs a Google search and returns a filtered list of results along with a summary answer.
๐ Features
โ LLM-ready tool with structured input/output
โ Works out-of-the-box with Claude Desktop, ChatGPT, or any MCP-compatible agent
โ Built using FastMCP
โ Real-world API integration via
GoogleSerperAPIWrapperโ Easy to extend with more tools
Related MCP server: SerpApi MCP Server
๐ฆ Requirements
Python 3.10+
A free Serper.dev API key
Optional: Claude Desktop for local tool calling
Optional: MCP Inspector for manual testing
๐ง Installation
Clone the repo:
git clone https://github.com/vikrambhat2/mcp-server-web-search.git cd mcp-server-web-search
2. Install dependencies:
pip install -r requirements.txt
3. Set environment variables in a `.env` file:
SERPER_API_KEY=your_serper_api_key_here PORT=10000
4. Run the server:
python server.py
---
## ๐ Tool Overview
This MCP server exposes a single tool: `google_search_tool`.
### ๐ค Input
```json
{
"input": "Your search query string"
}๐ฅ Output
{
"results": [
{
"title": "Result Title",
"link": "https://...",
"snippet": "Brief description"
},
...
],
"answer": "Concise answer generated by Serper"
}๐งช Testing
โ
With curl
curl -X POST http://localhost:10000/api/tools/google_search_tool \
-H "Content-Type: application/json" \
-d '{"input": "latest AI trends 2025"}'๐งช With Claude Desktop
Open Claude Desktop โ
Settings โ ToolcallingAdd your MCP server:
{ "mcpServers": { "googleSearch": { "url": "http://localhost:10000/mcp", "streaming": true } } }Ask Claude something like:
"Use the
google_search_toolto find top remote AI conferences in 2025."
๐งฐ With MCP Inspector (GUI)
Install MCP Inspector:
pip install mcp-inspector mcp-inspectorVisit
http://localhost:8080Paste in
http://localhost:10000/mcpExplore your tool, prompt, and test it with real inputs.
๐ Deployment (Optional)
You can deploy this server for free using Render:
Push this project to a GitHub repo
Create a new Web Service on Render
Add build/start commands:
Build:
pip install -r requirements.txtStart:
python app.py
Add environment variables:
SERPER_API_KEYPORT=10000
Your server will be live at:
https://yourproject.onrender.com/mcp
You can now plug it into Claude or your agents remotely.
๐ File Structure
โโโ app.py # Main MCP server script
โโโ .env # API key and port config
โโโ requirements.txt # Python dependencies
โโโ README.md # This file๐ References
๐ FastMCP
๐ Serper.dev
๐งช MCP Inspector
๐ค Claude + MCP Guide
๐ Maintainer
Built by @vikrambhat2 Pull requests and forks welcome!
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- 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/vikrambhat2/mcp-server-web-search'
If you have feedback or need assistance with the MCP directory API, please join our Discord server