Perplexity MCP Server O1e

The Perplexity MCP Server is a Python-based interface tool that provides functions to interact with the Perplexity API, supporting query responses, maintaining chat history, and managing conversations. You can configure the model through environment variables, and it has features such as local storage of chat data, streaming responses, and a Web UI.

Artificial intelligence chatbots Developer tools #API Interface #Chat Management #Model Configuration #Local Storage .Python

rating : 2 points

downloads : 19

update time : 2025-04-23

What is the Perplexity MCP Server?

The Perplexity MCP Server is a Python-based tool for programming problem-solving, chat record management, and model configuration through the Perplexity API. It allows users to interact with Perplexity AI just like in a browser.

How to use the Perplexity MCP Server?

Simply install Python and the uvx tool, then start using it according to the configuration file settings. It supports asking questions, maintaining chat history, and listing all conversations.

Applicable scenarios

Suitable for developers and researchers who need programming assistance, continuous conversation management, and technical problem-solving.

Main Features

Question-asking FunctionGet answers to programming questions through Perplexity AI, supporting source references and alternative suggestions.

Chat FunctionMaintain long-term conversations, supporting context continuity and history records.

Conversation ListList all available conversation records, displaying 50 records per page with pagination.

Read ConversationRetrieve the complete history of a specific conversation from the local database.

Web UIEasily manage conversations and settings through a graphical interface.

Advantages and Limitations

Advantages

Supports multiple model selection and configuration.

Has persistent chat history records.

Provides real-time progress reports to prevent timeouts.

Comes with a built-in Web UI for easy operation and management.

Limitations

Requires an API key to use.

Has a certain dependence on the network environment.

Advanced features may require more system resources.

How to Use

Install Python and the uvx tool

Ensure that Python 3.10 or a higher version is installed, and install uvx via pip.

Configure environment variables

Set necessary environment variables such as PERPLEXITY_API_KEY and PERPLEXITY_MODEL.

Start the server

Run the command to start the Perplexity MCP Server.

Usage Examples

Example 1: Debugging Python codeUse the ask_perplexity function to solve specific programming errors.

Example 2: Maintaining long-term conversationsUtilize the chat_perplexity function for continuous technical discussions.

Frequently Asked Questions

Do I need to register for an API key?

How do I enable the Web UI?

Does it support multi-model selection?

Related Resources

Official Documentation

Perplexity official documentation, providing more background information.

GitHub Repository

Project source code address, view the latest version and contribution guidelines.

Video Tutorial

Quick-start video to help you get started quickly.

🚀 Perplexity Chat MCP Server

The Perplexity Chat MCP Server offers a Python-based interface for interacting with Perplexity AI. It supports continuous conversations, chat history management, and Web UI functionality.

🚀 Quick Start

Use the Smithery command-line interface:

npx -y @smithery/cli@latest run @daniel-lxs/mcp-perplexity --config "{\"perplexityApiKey\":\"pplx-abc\",\"perplexityModel\":\"sonar-pro\"}"

✨ Features

ask_perplexity

The ask_perplexity tool is used to answer specific questions. Each request initiates a new conversation. It uses the PERPLEXITY_MODEL_ASK model (if specified) or the default PERPLEXITY_MODEL to generate responses.

chat_perplexity

The chat_perplexity tool supports continuous conversations and maintains chat history. Conversations are identified by a unique chat ID, such as wild-horse-12. It uses the PERPLEXITY_MODEL_CHAT model (if specified) or the default PERPLEXITY_MODEL to generate responses.

list_chats_perplexity

Lists all available conversations. It returns a paginated list of chats, showing the chat ID, title, and creation time (in relative format). You can specify the page number via the page parameter (default is 1, with 50 records per page).

read_chat_perplexity

Retrieves the complete conversation history based on the given chat_id. This tool does not call the Perplexity API and only reads data from the local database.

📦 Installation

Environment Variable Configuration

Property	Details
`WEB_UI_ENABLED`	Enable the Web UI
`WEB_UI_HOST`	Web UI host address
`WEB_UI_PORT`	Web UI port
`DEBUG_LOGS`	Enable detailed logging

💻 Usage Examples

ask_perplexity

The ask_perplexity tool is used to answer specific questions. Each request initiates a new conversation.

chat_perplexity

The chat_perplexity tool supports continuous conversations and maintains chat history. Conversations are identified by a unique chat ID, such as wild-horse-12.

list_chats_perplexity

Lists all available conversations. It returns a paginated list of chats, showing the chat ID, title, and creation time (in relative format).

read_chat_perplexity

Retrieves the complete conversation history based on the given chat_id. This tool does not call the Perplexity API and only reads data from the local database.

📚 Documentation

Web Interface

The Perplexity Chat MCP Server includes an interactive Web UI for more convenient chat management and interaction.

Features

Interactive chat interface
Chat history management
Real-time message display

Screenshots

Chat List View

Chat Interface

Accessing the Web Interface

When WEB_UI_ENABLED is set to true, the Web UI will be available at http://WEB_UI_HOST:WEB_UI_PORT. By default, this is http://127.0.0.1:8050.

Development

This project uses setuptools for development and building. Before you start:

Create a virtual environment:

python -m venv .venv
source .venv/bin/activate  # Run on macOS/Linux or powershell
.\.venv\Scripts\activate    # Run on Windows

Install dependencies:
```
pip install -r requirements.txt
```
Run tests:
```
pytest tests/
```

📄 License

This project is licensed under the MIT License.

📚 Citation

For citation, please refer to the literature.

Featured MCP Services

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

148

4.5 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

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.

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.

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.

572

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.

A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.

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

760

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご