Perplexica MCP Server

Name: Perplexica MCP Server
Author: thetom42

@thetom42

Repository

About Perplexica MCP Server

MCP server for Perplexica

#perplexica #mcp-server #ai-search

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "perplexica": {
      "command": "uvx",
      "args": [
        "perplexica-mcp",
        "stdio"
      ],
      "env": {
        "PERPLEXICA_BACKEND_URL": "http://localhost:3000/api/search"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Perplexica MCP Server?

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.

How to use Perplexica MCP Server?

Clone the repository, install dependencies with uv sync, and set the PERPLEXICA_BACKEND_URL environment variable to your running Perplexica instance. Run the server using one of three transport modes: uv run src/perplexica_mcp.py stdio, sse, or http. Configuration examples for Claude Desktop, Cursor IDE, and generic MCP clients are provided. Docker deployment is also supported with compose files for HTTP and SSE transports.

Key features of Perplexica MCP Server

AI-powered web search with multiple focus modes
Supports stdio, SSE, and Streamable HTTP transports
Built with FastMCP for robust MCP protocol compliance
Single unified server implementation for all transports
Docker support with health checks and security best practices

Use cases of Perplexica MCP Server

Add AI search to MCP-compatible clients like Claude Desktop or Cursor
Provide real-time search results over Server-Sent Events (SSE)
Integrate with REST workflows using Streamable HTTP transport
Deploy containerized search capabilities alongside Perplexica in Docker networks

FAQ from Perplexica MCP Server

What transports does Perplexica MCP Server support?

It supports stdio, SSE (Server-Sent Events), and Streamable HTTP transports. Stdio is recommended for most MCP clients; SSE and HTTP are available for web-based or real-time use cases.

How do I configure Perplexica MCP Server for my client?

Set the PERPLEXICA_BACKEND_URL environment variable to point to your Perplexica instance, then run the server with the appropriate transport command. For Claude Desktop or Cursor, use a stdio configuration with uv run ... stdio.

Does Perplexica MCP Server require a separate Perplexica instance?

Yes. The server connects to a running Perplexica instance via the PERPLEXICA_BACKEND_URL. You must ensure Perplexica is accessible at that URL.

How can I run Perplexica MCP Server in Docker?

Docker Compose files are provided for HTTP and SSE transports. Create an external Docker network named backend, set environment variables (e.g., PERPLEXICA_BACKEND_URL), then run docker-compose up -d. Both containers include health checks.