%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
MCP Perplexity Proxy Server
A Node.js proxy server that forwards OpenAI-compatible or MCP native requests to the Perplexity AI Sonar model and supports streaming.
rating : 2 points
downloads : 22
What is the MCP Perplexity Proxy Server?
This is a middleware server that allows developers to access the Perplexity AI Sonar model through an OpenAI-compatible API or the MCP native API. It simplifies the AI model integration process, especially suitable for application scenarios that require streaming responses.How to use the MCP Perplexity Proxy Server?
You can quickly deploy a local service via Docker and then send requests using the standard OpenAI API format or the MCP native API format.Use Cases
Suitable for development environments that need to quickly integrate the capabilities of Perplexity AI, especially when using development tools such as Cursor, CLine, or RooCode.Main Features
OpenAI API CompatibilityFully compatible with OpenAI's /v1/chat/completions interface, facilitating the migration of existing applications
MCP Native Streaming InterfaceProvides an /mcp-stream endpoint optimized for streaming
One-Click Docker DeploymentEnables rapid local deployment via docker-compose
Swagger UI SupportBuilt-in API documentation interface for easy testing and debugging
Advantages and Limitations
Advantages
Seamlessly integrate with existing OpenAI ecosystem tools
Support streaming to enhance the response experience
Local deployment ensures data privacy
Simplify the process of accessing Perplexity AI models
Limitations
Requires local server resources to run
Only supports the Sonar model series of Perplexity AI
The streaming interface requires special handling
How to Use
Start the Service
Start the proxy service using Docker Compose
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%230080ff;%20}%20%3c/style%3e%3c/defs%3e%3cpath%20class='st0'%20d='M16.2,11.1c.4.5.4,1.2,0,1.8l-4.7,7.1h-3.8l5.3-8L7.6,4h3.8l4.7,7.1Z'/%3e%3c/svg%3e)
Configure the Client
Configure the API endpoint in tools such as CLine/Cursor/RooCode
Send a Request
Send a request using the OpenAI-compatible format or the MCP native format
Usage Examples
Code ExplanationAsk the AI for explanations of programming concepts or code snippets
Development Tool IntegrationUse it as an AI assistant tool in IDEs such as Cursor
Streaming Chat ApplicationBuild a chat application that needs to display AI responses in real-time
Frequently Asked Questions
Why is this proxy service needed?
How are API keys handled?
Which Sonar models are supported?
How to monitor the service status?
Related Resources
Perplexity AI Official Documentation
Official technical documentation of Perplexity AI
OpenAI API Reference
Official reference documentation of the OpenAI API
GitHub Repository
Project source code and issue tracking
Docker Documentation
Official Docker documentation
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
1.8K
5 points
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
876
4.3 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
136
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
186
4.5 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
6.7K
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#
600
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
787
4.8 points
Gmail MCP Server
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.
TypeScript
322
4.5 points