Perplexity

A server that implements the MCP protocol to bring perplexity API into context.

typescript

6

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "laodev1-perplexity-mcp-server": {
      "command": "node",
      "args": [
        "path\\\\to\\\\perplexity-mcp-server\\\\dist\\\\index.js"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY"
      }
    }
  }
}

You run a secure MCP bridge that lets Claude talk to Perplexity AI’s language models. This server implements the Model Context Protocol (MCP) so you can call Perplexity tools from Claude and manage tool usage safely within an MCP session.

How to use

You connect to the Perplexity MCP Server through an MCP client. Once loaded, the server exposes two tools for interaction: perplexity_chat for full message history based chat, and perplexity_ask for quick single queries. Use perplexity_chat when you want to maintain context across turns and perplexity_ask for concise, single-turn questions. The server handles input validation, error reporting, and secure execution of tool calls.

In your client dialog, request tool invocations by name according to the task you want to perform. The server validates inputs against the tool schemas and returns structured responses or error messages as appropriate.

How to install

Prerequisites you need before installing: Node.js installed on your system (version compatible with the server’s TypeScript setup). Ensure you have npm available to install dependencies.

# Step 1: Clone the project repository
git clone https://github.com/yourusername/perplexity-mcp-server.git
cd perplexity-mcp-server

# Step 2: Install dependencies
npm install

# Step 3: Create environment file and add your Perplexity API key
# (The environment file is loaded by the server at runtime)

Additional sections

Configuration, security, and troubleshooting follow these guidelines to ensure reliable operation and safe tool usage.

Build and run flow: you build the project, then start the server using the runtime command described in the configuration snippet.

Environment variables: you provide your Perplexity API key via an environment variable named PERPLEXITY_API_KEY. The server uses this key to authenticate requests to Perplexity AI.

Available tools

perplexity_chat

Generate a chat completion using Perplexity AI with full message history support, suitable for multi-turn conversations.

perplexity_ask

Send a simple single-question prompt to Perplexity AI for quick answers.