Traylinx Search Engine MCP Server
Description
# Traylinx Search Engine MCP Server [](https://smithery.ai/server/traylinx/traylinx-search-engine-mcp-server) A Model Context Protocol (MCP) server that acts as a bridge to the deployed…
About
# Traylinx Search Engine MCP Server [](https://smithery.ai/server/traylinx/traylinx-search-engine-mcp-server) A Model Context Protocol (MCP) server that acts as a bridge to the deployed **Agentic Search API**. It allows MCP clients…
Details
- Author
- traylinx
- Downloads
- 179
- Categories
- Search
Jump to
- Rich content types: text, HTML, images, news
- Time filtering by month, week, day, hour
- Secure API key via environment variables
- Configurable API endpoint URL
- Full MCP protocol compliance
- Supports multiple structured response types
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Traylinx Search Engine MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Node.js 18+, obtain an API key from Traylinx.com, clone the repository, run npm install and npm build. Configure your MCP client (Claude Desktop or Cursor) with environment variables AGENTIC_SEARCH_API_KEY, AGENTIC_SEARCH_API_URL, and optionally LOG_LEVEL. Invoke the search tool with a query and an optional search_recency_filter parameter.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"traylinx search engine mcp server": {
"traylinx-search-engine-mcp-server": {
"command": "node",
"args": [
"path/to/traylinx-search-engine-mcp-server/dist/index.js"
],
"env": {
"AGENTIC_SEARCH_API_KEY": "<YOUR_TOKEN>",
"AGENTIC_SEARCH_API_URL": "https://agentic-search-engines-n3n7u.ondigitalocean.app",
"LOG_LEVEL": "INFO"
}
}
}
}
}
McpServers
{
"traylinx-search-engine-mcp-server": {
"command": "node",
"args": [
"path/to/traylinx-search-engine-mcp-server/dist/index.js"
],
"env": {
"AGENTIC_SEARCH_API_KEY": "<YOUR_TOKEN>",
"AGENTIC_SEARCH_API_URL": "https://agentic-search-engines-n3n7u.ondigitalocean.app",
"LOG_LEVEL": "INFO"
}
}
}
Traylinx Search Engine MCP Server
A Model Context Protocol (MCP) server that acts as a bridge to the deployed Agentic Search API. It allows MCP clients like Claude Desktop and Cursor to utilize intelligent search capabilities with both text summaries and structured data (HTML, images, and more).
Tools
search
Perform a web search using Traylinx's API, which provides detailed and contextually relevant results with citations. By default, no time filtering is applied to search results.
Inputs:
- query (string): The search query to perform.
- search_recency_filter (string, optional): Filter search results by recency. Options: "month", "week", "day", "hour". If not specified, no time filtering is applied.
How it Works
1. You configure this MCP server with your Agentic Search API URL and API Key (via environment variables passed by the client config).
2. An MCP client (e.g., Claude) sends a tool call to this server with a search query and optional recency filter.
3. This MCP server makes a request to the Agentic Search API with the query and authorization header.
4. It parses the rich response (text, HTML, search results, media, news) and returns structured content to the MCP client.
Installation
Prerequisites
Node.js >= 18.0.0
An API Key from Traylinx.com
Step 1: Get an API Key from Traylinx
1. Visit traylinx.com and sign up for an account
2. Navigate to the developer dashboard/API section
3. Generate your API key for the Agentic Search API
4. Keep this key secure - you'll need it for configuration
Step 2: Set Up the MCP Server
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.

