Perplexity

Exposes Perplexity AI search capabilities to Claude via an MCP server for integrated querying.

python

0

GitHub Stars

python

Language

4 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": {
    "shaunmacfullstack-claude-perplexity-mcp": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

This MCP server exposes Perplexity AI's search capabilities to Claude, enabling you to query Perplexity data through an MCP client and receive integrated results within Claude workflows.

How to use

You interact with the Perplexity MCP server by connecting an MCP client to the local server process. Run the server on your machine or a development environment, then point your MCP client at the local Python process. The server reads your Perplexity API key from the environment and provides search capabilities to your Claude-driven prompts.

How to install

Prerequisites you need before installing:
- Python 3.8+ installed on your system
- pip available to install dependencies
- Access to Perplexity API with a valid API key

Step-by-step installation and startup commands:

Clone the project repository
Copy the example environment file to create your own .env
Install required Python dependencies
Run the MCP server using Python

# Step 1: Clone the repository
git clone https://example.com/shaunmacfullstack/claude-perplexity-mcp.git
cd claude-perplexity-mcp

# Step 2: Create environment file from template
cp .env.example .env
# Edit .env and insert your Perplexity API key

# Step 3: Install dependencies
pip install -r requirements.txt

# Step 4: Start the MCP server
python server.py

Configuration

Configuration options are defined in the environment file. Create a copy of the example and provide your Perplexity API key as the primary credential. The server reads the API key from the environment when starting.

Security

Follow best practices for handling API keys: keep the .env file secure, restrict access to the host running the MCP server, and avoid exposing the server port to untrusted networks. Regularly rotate API keys and monitor usage for anomalies.

Troubleshooting

If the server fails to start, verify that Python is installed, dependencies resolved, and the Perplexity API key is correctly set in the environment. Check for common issues such as missing dependencies or invalid API keys, and review error messages from the Python process for guidance.

Available tools

Perplexity API client

Handles communication with the Perplexity API, including constructing requests and parsing responses.

MCP server implementation

Provides the bridge between Claude via MCP and Perplexity search capabilities, including key management and request routing.