Perplexica MCP Server
About
Perplexica MCP Server is a Model Context Protocol (MCP) server that provides AI-powered web search functionality by connecting MCP clients to the Perplexica search API. It supports stdio, SSE, and Streamable HTTP transports and is built with the FastMCP framework.
Details
- License
- MIT license
Explore
- Search Tool: AI-powered web search with multiple focus modes
- Multiple Transport Support: stdio, SSE, and Streamable HTTP transports
- FastMCP Integration: Built using FastMCP for robust MCP protocol compliance
- Unified Architecture: Single server implementation supporting all transport modes
- Production Ready: Docker support with security best practices
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
Perplexica 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
uv sync
To use this server with MCP clients, you need to configure the client to connect to the Perplexica MCP server. Below are configuration examples for popular MCP clients.
For any MCP client supporting stdio transport:
PERPLEXICA_BACKEND_URL=http://localhost:3000/api/search
For HTTP/SSE transport clients:
1. Path Configuration: Replace /path/to/perplexica-mcp/ with the actual path to your installation
2. Perplexica URL: Ensure PERPLEXICA_BACKEND_URL points to your running Perplexica instance
3. Transport Selection:
- Use stdio for most MCP clients (Claude Desktop, Cursor)
- Use SSE for web-based clients or real-time applications
- Use HTTP for REST API integrations
4. Dependencies: Ensure uv is installed and available in your PATH
Create a .env file in the project root with your Perplexica configuration:
PERPLEXICA_BACKEND_URL=http://localhost:3000/api/search
The server includes Docker support with multiple transport configurations for containerized deployments.
Both Docker configurations support environment variables:
networks:
- backend
perplexica-mcp:
environment:
- PERPLEXICA_BACKEND_URL=http://perplexica-app:3000/api/search
networks:
- backend
```
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"perplexica mcp server": {
"perplexica": {
"command": "uvx",
"args": [
"perplexica-mcp",
"stdio"
],
"env": {
"PERPLEXICA_BACKEND_URL": "http://localhost:3000/api/search"
}
}
}
}
}McpServers
{
"perplexica": {
"command": "uvx",
"args": [
"perplexica-mcp",
"stdio"
],
"env": {
"PERPLEXICA_BACKEND_URL": "http://localhost:3000/api/search"
}
}
}A Model Context Protocol (MCP) server that provides search functionality using Perplexica's AI-powered search engine.
Features
- Search Tool: AI-powered web search with multiple focus modes
- Multiple Transport Support: stdio, SSE, and Streamable HTTP transports
- FastMCP Integration: Built using FastMCP for robust MCP protocol compliance
- Unified Architecture: Single server implementation supporting all transport modes
- Production Ready: Docker support with security best practices
Installation
```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.
