Coding With Perplexity AI MCP server

The Perplexity MCP Server provides intelligent code analysis and debugging capabilities using Perplexity AI's API, working seamlessly with the Claude desktop client. It offers detailed error analysis, pattern detection, comprehensive solutions, and best practices recommendations, with specialized support for Python.

Features

• Intelligent Error Analysis: Detailed breakdown of coding errors with root cause analysis
• Pattern Detection: Automatically recognizes common error patterns and provides targeted solutions
• Comprehensive Solutions: Step-by-step fixes with multiple implementation alternatives
• Best Practices: Includes coding standards and error prevention tips
• Python Support: Specialized handling of Python type errors and common coding issues

Example Usage

Ask questions like:

• "Fix this TypeError in my Python code"
• "What's causing this error message?"
• "How do I fix this code?"

Include your code snippet for targeted analysis:

def calculate_total(items):
    total = 0
    for item in items:
        total = total + item['price']  # TypeError: string + int

data = [
    {'name': 'Book', 'price': '10'},
    {'name': 'Pen', 'price': '2'}
]

result = calculate_total(data)

The server will provide:

1. Root cause analysis of the error
2. Step-by-step solution with code examples
3. Best practices to prevent similar issues
4. Alternative implementation approaches

Installation

Prerequisites

• Node.js 18 or higher
• A Perplexity AI API key

Option 1: Install from npm (Recommended)

# Using npm
npm install -g perplexity-mcp

# Or using the repository directly
npm install -g git+https://github.com/yourusername/perplexity-mcp.git

Option 2: Install from Source

1. Clone the repository:

git clone https://github.com/yourusername/perplexity-server.git
cd perplexity-server

2. Install dependencies:

npm install

3. Build and install globally:

npm run build
npm install -g .

Configuring Claude Desktop

Add to your Claude desktop configuration file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "perplexity": {
      "command": "perplexity-mcp",
      "args": [],
      "env": {
        "PERPLEXITY_API_KEY": "your-api-key-here"
      }
    }
  }
}

Or if installed from source:

{
  "mcpServers": {
    "perplexity": {
      "command": "node",
      "args": ["/absolute/path/to/perplexity-server/build/index.js"],
      "env": {
        "PERPLEXITY_API_KEY": "your-api-key-here"
      }
    }
  }
}

Security Notes

• The API key is stored securely in Claude's desktop configuration file
• The key is passed to the server as an environment variable
• No sensitive data is stored in the repository
• The server expects the API key to be provided by Claude's environment

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.