Happy slice of mcp pizzaMCP.pizza

perplexity-deep-research

MCP.Pizza Chef: arjunkmrm

Perplexity Deep Research MCP server integrates Perplexity AI's chat completions API with the sonar-deep-research model, enabling AI assistants to perform advanced web searches. It provides a 'deep_research' tool that accepts search queries and optional recency filters, returning relevant, up-to-date web search results. This server requires a Perplexity API key and supports real-time, context-rich web research for AI workflows.

Use This MCP server To

Perform web searches using Perplexity AI's deep research model Filter search results by recency (month, week, day, hour) Integrate real-time web search into AI assistant workflows Retrieve detailed web search results for complex queries Enable AI models to access current web information dynamically

README

Perplexity Deep Research MCP

smithery badge

A Model Context Protocol (MCP) server for Perplexity AI API with web search capabilities. This server allows AI assistants to perform web searches using Perplexity's chat completions API with the sonar-deep-research model.

Features

  • Provides a deep_research tool for AI assistants to perform web searches
  • Uses Perplexity's chat completions API with the sonar-deep-research model

Tool: deep_research

The server provides a deep_research tool with the following input parameters:

  • query (required): The search query to perform
  • search_recency_filter (optional): Filter search results by recency (options: month, week, day, hour)

Configuration

Environment Variables

  • PERPLEXITY_API_KEY: Your Perplexity API key (required)

Response Format

The response from the deep_research tool includes:

  • Content of search results
  • Citations for the information

Installing via Smithery

To install perplexity-deep-research for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @arjunkmrm/perplexity-deep-research --client claude

License

MIT

perplexity-deep-research FAQ

How do I configure the Perplexity Deep Research MCP server?
Set the PERPLEXITY_API_KEY environment variable with your Perplexity API key to enable API access.
What input parameters does the deep_research tool accept?
It requires a 'query' string and optionally a 'search_recency_filter' to limit results by time.
Can I filter search results by how recent they are?
Yes, you can filter results by month, week, day, or hour using the search_recency_filter parameter.
What model does this MCP server use for web searches?
It uses Perplexity's sonar-deep-research model via their chat completions API.
Is this MCP server compatible with multiple LLM providers?
Yes, it can be integrated with various LLMs like OpenAI, Anthropic Claude, and Google Gemini to enhance AI assistant capabilities.
What kind of responses does the deep_research tool return?
It returns structured web search results relevant to the query, formatted for AI consumption.