perplexity-webui-scraper
Active·★ 137·MIT·Updated 2026-10-20
★ Hidden Gem
This Python library programmatically interacts with Perplexity AI's web interface, enabling features like conversations, file uploads, and streaming without requiring an official API key. It also provides an OpenAI-compatible REST API and an MCP server for AI agents, effectively acting as a bridge to Perplexity AI.
#Python#Web Scraping#LLM Integration#Perplexity AI#API Wrapper#OpenAI Compatible#AI Agents#Streaming
01
Features
01Programmatically interact with Perplexity AI using web endpoints, bypassing the need for an official API key.
02Supports core functionalities including multi-turn conversations, file attachments (images, PDFs), and real-time streaming of AI responses.
03Offers an OpenAI-compatible REST API server, allowing existing OpenAI clients to easily integrate with Perplexity AI.
04Includes an MCP (Multi-Agent Communication Protocol) server to expose Perplexity models as tools for AI agents.
05Manages model availability and account tier compatibility, adapting to free or paid Perplexity accounts.
02
Compatibility
Python
Runtime
Verified via docs
Docker
Deployment
Verified via docs
Podman
Deployment
Verified via docs
03
Quick start
1
$ uv add "perplexity-webui-scraper[all]"
04
Use cases
↳Develop custom applications or bots that leverage Perplexity AI's capabilities without an official API subscription.
↳Automate data extraction or content generation tasks from Perplexity AI's web interface.
↳Integrate Perplexity AI into multi-agent systems by using the provided MCP server.
↳Migrate existing OpenAI API-dependent applications to use Perplexity AI as a backend with minimal code changes.
05
Alternatives
⚡Top VS:
livetennisapi-mcp★ 152
MCP server for the Live Tennis API — give Claude, Cursor and other LLM agents real-time tennis scores, odds and model win-probability
gopher-mcp★ 15
A modern, cross-platform Model Context Protocol (MCP) server that enables AI assistants to browse and interact with both Gopher protocol and Gemini protocol resources safely and efficiently.
google-analytics-mcp★ 243
Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.
mcp-dotnet-samples★ 201
A comprehensive set of samples of creating and using MCP servers and clients with .NET
ltspice-mcp★ 63
MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice
Comments
Log in to leave a comment
No comments yet. Be the first!