An async Python client for Brave Search that provides streaming AI answers and structured web search with a built-in Model Context Protocol (MCP) server.

Stars

43

7-day growth

No data

Forks

10

Open issues

0

License

NOASSERTION

Last updated

2026-07-15

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines AI-powered streaming answers, web search, and an MCP server in a single typed interface without requiring an API key, using browser fingerprinting for authentication.

Who it is for

  • Python developers building AI-powered search applications
  • LLM agent developers needing web search integration
  • MCP-compatible client users (Claude Desktop, Claude Code, Cursor)
  • Developers seeking privacy-respecting search without API keys

Use cases

  • Building AI-driven search assistants with real-time streaming answers
  • Integrating Brave Search into chatbot or agent pipelines
  • Running an MCP server to expose search and AI capabilities to LLM tools
  • Scraping structured web and news results with pagination

Strengths

  • Async-native with real-time streaming support (typewriter output)
  • No API key required; uses browser fingerprinting via curl_cffi
  • Comprehensive MCP server supporting both stdio and HTTP/SSE transports
  • Rich type safety with Pydantic models and structured error hierarchy

Considerations

  • Requires Python 3.11 or later
  • Relies on Brave's external service, which may impose rate limits or CAPTCHA challenges
  • Proxy pool complexity may require careful configuration for reliability

README quick start

Installation

Description

Brave API is totally free. No login. No API key. No bullshit.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482