Perplexica MCP Server

A Model Context Protocol (MCP) server for interacting with local Perplexica instances. This server provides tools to perform AI-powered searches

Local serverstdioPython

What is the Perplexica MCP MCP server?

Perplexica MCP becomes available to MCP clients through the perplexica mcp mcp server. A Model Context Protocol (MCP) server for interacting with local Perplexica instances. This server provides tools to perform AI-powered searches using your local Perplexica installation.

What Perplexica MCP does

A Model Context Protocol (MCP) server for interacting with local Perplexica instances. This server provides tools to perform AI-powered searches using your local Perplexica installation.

Key capabilities

  • Search — Perform AI-powered searches with various focus modes
  • Streaming Support — Get real-time streaming responses
  • Multiple Focus Modes — Support for web search, academic search, writing assistant, and more
  • Customizable Models — Configure chat and embedding models
  • Conversation History — Maintain context across searches

Tools it exposes

Once connected, the assistant can call these 2 tools directly:

  • perplexica_search — Perform AI-powered searches with various focus modes
  • perplexica_get_models — Get available chat and embedding models

Installing the perplexica mcp mcp server

The server is distributed via PyPI as git, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply one environment variable: PERPLEXICA_BASE_URL. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

Where it fits

AI-service servers chain other models into your assistant, turning a single chat into a small production pipeline. Perplexica MCP sits in that group, and the shape of its toolset — perplexica_search, perplexica_get_models — tells you what it is really for. Worth comparing against the other ai services servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by armand0e, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the perplexica mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
perplexica_searchPerform AI-powered searches with various focus modes
perplexica_get_modelsGet available chat and embedding models

How to install the Perplexica MCP MCP server

{
  "mcpServers": {
    "perplexica": {
      "command": "uvx",
      "args": ["git"],
      "env": {
        "PERPLEXICA_BASE_URL": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
PERPLEXICA_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Perplexica MCP to perplexica search.
  • Use Perplexica MCP to perplexica get models.

Frequently asked questions

It connects Perplexica MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (perplexica_search, perplexica_get_models) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Perplexica MCP directly.