OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

Perplexity Python Wrapper (helallao)

An MIT-licensed, public Python library that unofficially wraps Perplexity.ai and includes a web interface, account-generation workflow and MCP server.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Perplexity Python Wrapper (helallao) — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a Python integration or MCP connection to Perplexity.ai is more useful than manually using the website, especially when synchronous, asynchronous or streaming access is needed.

Who it is for

  • Python developers integrating Perplexity.ai queries into applications
  • Teams building synchronous or asynchronous research-query services
  • Users connecting Perplexity search to local or HTTP MCP clients

Documented uses

  • Send Perplexity.ai queries from synchronous Python code
  • Run asynchronous queries and stream response chunks
  • Expose question answering, research, reasoning and search through MCP
  • Use a browser-based interface for documented query and account workflows
Before you choose

Requirements & limits

The repository is public, marked MIT-licensed and documents installation with uv. Anonymous MCP operation is documented for free auto-mode queries; cookies are required for the documented pro, reasoning and deep-research modes.

  • It provides both synchronous and asynchronous Python APIs.
  • The MCP server supports stdio and HTTP transports.
  • The documented interface uses a reverse-engineered web interface rather than an official API key.
  • MCP responses are plain text and several official-server options are unavailable, including domain and recency filters, structured citations and image results.
  • Optional web-interface driver support requires the documented driver extra and Chromium installation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the MCP server and run it locally

Set up the included MCP server for a local MCP client using the documented stdio transport.

Before you start

  • Python 3.10 or newer is indicated by the repository badge.
  • The project source and uv-based installation workflow.
  • A local MCP client such as Claude Code or Claude Desktop.

Steps

  1. Install the project with the MCP extra using the command below, or install it as a tool with the command below.

    Documented command
    uv sync --extra mcp
    Documented command
    uv tool install '.[mcp]'

  2. Run perplexity-mcp; stdio is the default transport.

  3. Add the server to Claude Code with claude mcp add perplexity -- perplexity-mcp, or use the documented manual configuration.

  4. Optionally provide PERPLEXITY_COOKIES as a JSON string when pro, reasoning or deep-research modes are required.

Expected outcome

A local MCP client can access the server’s documented Perplexity tools, with anonymous auto-mode queries when cookies are not provided.

Guide limitations

  • Without cookies, the README documents access to free auto-mode queries only.
  • The server uses a single query string and returns plain-text answers rather than structured citations or images.
  • This is a reverse-engineered web-interface approach, not the official paid API-key MCP server.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
helallao/perplexity-ai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction