mcpField
🚀
🚀 MCP Perplexity Proxy Server

🚀 MCP Perplexity Proxy Server

Local
github.com/nikolaospapagiannisAI & Agents0Updated 82w ago

About 🚀 MCP Perplexity Proxy Server

MCP Perplexity Proxy Server is a Node.js proxy for sending OpenAI-compatible or MCP-native requests to Perplexity AI Sonar models. It supports streaming and provides HTTP endpoints for chat completions, MCP requests, and Swagger UI.

Key features

  1. 01Proxy requests to Sonar models
  2. 02OpenAI-compatible chat completions endpoint
  3. 03MCP-native streaming endpoint
  4. 04Swagger UI endpoint

Use cases

  1. 01Connect compatible clients to Perplexity Sonar
  2. 02Stream MCP-native requests
  3. 03Explore the API through Swagger UI

MCP support

It accepts MCP-native requests at `/mcp-stream` and streams responses from Perplexity AI Sonar models.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🚀 MCP Perplexity Proxy Server

This Node.js server proxies OpenAI-compatible or MCP-native requests to Perplexity AI's Sonar models with streaming support.

🔧 Run locally

docker-compose up --build

🔁 Supported APIs

  • POST /v1/chat/completions (OpenAI-compatible)
  • POST /mcp-stream (MCP-native)
  • GET / (Swagger UI)

✅ Usage in CLine / Cursor / RooCode

{
  "provider": "openai",
  "api_base": "http://localhost:3000/v1",
  "api_key": "dummy"
}

🧪 Local Testing

curl -X POST http://localhost:3000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"sonar-reasoning-pro","messages":[{"role":"user","content":"Was ist JSON.stringify?"}]}'

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.