Perplexity MCP
An MCP server based on the Perplexity AI API, providing web search functionality for the Claude desktop client.
rating : 4.1 points
downloads : 261
What is Perplexity MCP?
Perplexity MCP is a Model Context Protocol (MCP) server that provides web search functionality through the Perplexity AI API. You can use it to search for the latest news, research, or other online information.How to use Perplexity MCP?
Simply enter specific search prompts in the Claude desktop client, such as 'Search for news about OpenAI in the past week', to get relevant results.Applicable Scenarios
Suitable for researchers, students who need to quickly obtain the latest information, and anyone who wants to know the latest developments on a specific topic.Main Features
Web SearchUtilize the powerful API of Perplexity AI to achieve efficient web searches.
Advantages and Limitations
Advantages
Get the latest information on the Internet in real - time.
Support filtering by various time ranges, such as days, weeks, months, or years.
Easy to use, no complex configuration is required to start using.
Limitations
Requires a valid Perplexity API key to run.
Some advanced features may be limited to paid users.
How to Use
Install Dependent Tools
Make sure UV (Fast Python package manager) is installed. It can be installed via Homebrew or the official script.
Configure Environment Variables
Set the PERPLEXITY_API_KEY environment variable, which is necessary to access the Perplexity API.
Start the MCP Server
Use the Smithery CLI tool to install and start the Perplexity MCP server.
Usage Examples
Case TitleDemonstrate how to use Perplexity MCP for web searches in the Claude desktop client.
Case TitleShow how to use the time - range filtering function to obtain information for a specific time period.
Frequently Asked Questions
How to obtain a Perplexity API key?
Does it support custom search models?
Related Resources
Perplexity AI Official Website
Learn about Perplexity AI and its API services.
Claude Desktop Client
Download and install the Claude desktop client.
GitHub Repository
View the source code of the Perplexity MCP server.
Featured MCP Services

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
75
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
820
4.3 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
124
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
551
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.6K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
743
4.8 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points