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., "@Synthetic Web Search MCP Serversearch for the latest news about OpenAI's Sora"
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.
Synthetic Web Search MCP Server
A Model Context Protocol (MCP) server that exposes the Synthetic web search API as a tool for use with Claude and other MCP-compatible applications.
Overview
This server provides a search_web tool that allows MCP clients to perform web searches using the Synthetic API. Search results are returned as formatted JSON containing URL, title, text, and published date fields.
Installation
Install globally to use with any MCP client:
Or with Bun:
Quick Start with Claude Code
Add the MCP server to Claude Code with a single command:
Replace your_api_key_here with your actual Synthetic API key.
Configuration
The server requires a Synthetic API key. Set it using the SYNTHETIC_API_KEY environment variable:
Or create a .env file in the project root (copy .env.example):
Usage with Claude Desktop
To use this MCP server with Claude Desktop, add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
If installed locally (not globally), use:
After adding the configuration, restart Claude Desktop. You can then use the web search tool in your conversations.
Testing with MCP Inspector
To test the server without Claude Desktop, use the MCP inspector:
This will open a web interface where you can:
List available tools
Test the
search_webtool with different queriesView returned results in real-time
Available Tools
search_web
Search the web using the Synthetic API.
Arguments:
query(string, required): The search query string
Example:
Returns: A JSON array of search results, each containing:
url: The link to the search resulttitle: The title of the pagetext: A snippet or content from the pagepublished: Publication date (if available)
API Details
Endpoint:
https://api.synthetic.new/v2/searchMethod: POST
Authentication: Bearer token via
AuthorizationheaderRequest Body: JSON with
queryfield
Development
Setup the development environment:
Build the project:
Run the dev server with ts-node:
Watch for file changes and rebuild automatically: