Perplexity MCP Server: Real-Time Search & Seamless AI Integration

Supercharge apps with real-time web search! Our MCP server merges Perplexity AI's power for seamless integration, delivering instant answers that drive smarter decisions. Launch now!

Visit Repository

✨ Research And Data

4.2(24 reviews)

36 saves

16 comments

Users create an average of 14 projects per month with this tool

About Perplexity MCP Server

What is Perplexity MCP Server: Real-Time Search & Seamless AI Integration?

Perplexity MCP Server is a specialized tool built on the Model Context Protocol (MCP) framework, designed to integrate real-time web search capabilities with AI-driven platforms like the Claude desktop client. It leverages Perplexity AI's advanced search API to deliver up-to-date information directly within conversational AI interfaces. This server acts as a bridge between dynamic data retrieval and natural language processing, enabling users to request real-world information seamlessly during AI-assisted interactions.

How to Use Perplexity MCP Server: Real-Time Search & Seamless AI Integration?

Install via Smithery: Run npx @smithery/cli install perplexity-mcp to set up the server environment.
Configure dependencies: Ensure Node.js and UV (utility toolkit) are installed; use npm install -g uv if missing.
Set environment variables: Add PERPLEXITY_API_KEY and optionally specify models like perplexity:latest in your config files.
Integrate with clients: Modify configuration files for Cursor or Claude Desktop to register the server endpoint. Test with prompts like "Search for recent AI breakthroughs".

Perplexity MCP Server Features

Key Features of Perplexity MCP Server: Real-Time Search & Seamless AI Integration?

Dynamic Query Handling: Supports query parameters and temporal filters via recency (e.g., past week/month).
Model Flexibility: Choose from multiple Perplexity models (e.g., perplexity:latest) for varying search depth/accuracy.
Granular Permissions: Requires explicit user consent for each tool invocation through in-chat confirmation dialogs.
CI/CD Ready: Pre-configured for deployment with Smithery CLI and dependency management via npm.

Use Cases of Perplexity MCP Server: Real-Time Search & Seamless AI Integration?

Common applications include:

Real-time news aggregation during crisis management scenarios
Market research with automated competitor analysis through keyword tracking
Assisted content creation using verified web sources within AI writing tools
Automated report generation with dynamically sourced data

Perplexity MCP Server FAQ

FAQ from Perplexity MCP Server: Real-Time Search & Seamless AI Integration?

Where do I find my Perplexity API key?: Login to Perplexity's developer portal and navigate to API credentials section.
Can I use this with non-Claude platforms?: Yes, but requires custom integration with MCP-compatible interfaces. The server is protocol-agnostic by design.
What happens if the API rate limit is exceeded?: Responses return 429 Too Many Requests errors. Implement exponential backoff or upgrade your API plan for higher limits.
How do I troubleshoot configuration issues?: Check ~/.smithery/logs for deployment errors. Validate JSON syntax in claude_desktop_config.json files.

Content

perplexity-mcp MCP server

A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Works with the Anthropic Claude desktop client.

Example

Let's you use prompts like, "Search the web to find out what's new at Anthropic in the past week."

Glama Scores

Components

Prompts

The server provides a single prompt:

perplexity_search_web: Search the web using Perplexity AI
- Required "query" argument for the search query
- Optional "recency" argument to filter results by time period:
  - 'day': last 24 hours
  - 'week': last 7 days
  - 'month': last 30 days (default)
  - 'year': last 365 days
- Uses Perplexity's API to perform web searches

Tools

The server implements one tool:

perplexity_search_web: Search the web using Perplexity AI
- Takes "query" as a required string argument
- Optional "recency" parameter to filter results (day/week/month/year)
- Returns search results from Perplexity's API

Installation

Installing via Smithery

To install Perplexity MCP for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install perplexity-mcp --client claude

Requires UV (Fast Python package and project manager)

If uv isn't installed.

# Using Homebrew on macOS
brew install uv

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Environment Variables

The following environment variable is required in your claude_desktop_config.json. You can obtain an API key from Perplexity

PERPLEXITY_API_KEY: Your Perplexity AI API key

Optional environment variables:

PERPLEXITY_MODEL: The Perplexity model to use (defaults to "sonar" if not specified)

Available models:

* `sonar-deep-research`: 128k context - Enhanced research capabilities
* `sonar-reasoning-pro`: 128k context - Advanced reasoning with professional focus
* `sonar-reasoning`: 128k context - Enhanced reasoning capabilities
* `sonar-pro`: 200k context - Professional grade model
* `sonar`: 128k context - Default model
* `r1-1776`: 128k context - Alternative architecture

And updated list of models is avaiable (here)[https://docs.perplexity.ai/guides/model-cards]

Cursor & Claude Desktop Installation

Add this tool as a mcp server by editing the Cursor/Claude config file.

  "perplexity-mcp": {
    "env": {
      "PERPLEXITY_API_KEY": "XXXXXXXXXXXXXXXXXXXX",
      "PERPLEXITY_MODEL": "sonar"
    },
    "command": "uvx",
    "args": [
      "perplexity-mcp"
    ]
  }

Cursor

On MacOS: /Users/your-username/.cursor/mcp.json
On Windows: C:\Users\your-username\.cursor\mcp.json

If everything is working correctly, you should now be able to call the tool from Cursor. mcp_screenshot

Claude Desktop

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

To verify the server is working. Open the Claude client and use a prompt like "search the web for news about openai in the past week". You should see an alert box open to confirm tool usage. Click "Allow for this chat".