brave-api — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by iqbalmh18 · MCP Server · ★ 51

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is brave-api safe to install? View the security audit →

About brave-api

Brave API An async Python client for Brave Search, providing streaming AI answers and structured web search in a single, typed interface — with a built-in Model Context Protocol (MCP) server. Table of Contents Features Architecture Requirements Installation Quick Start Ask Search Client Configuration Proxy Support Conversation Streaming Events StreamResult Error Handling MCP Server [Project Structure](#project-

bravebrave-apibrave-askbrave-browserbrave-gogglebrave-mcpbrave-search-aimcpmcp-clientmcp-server

Quick Facts

Stars51
Forks11
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score70.7866238021275/100
Last Updated2026-08-21
Created2026-07-05
Platformsbrowser, cli, mcp, python
Est. Tokens~18k

Compatible Skills

These tools work well together with brave-api for enhanced workflows:

  • relevanceai — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

brave-api alternative? Top 6 similar tools

Looking for a brave-api alternative? If you're comparing brave-api with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • MCP-Defender by MCP-Defender · ⭐ 255

    Desktop app that automatically scans and blocks malicious MCP traffic in AI apps like Cursor, Claude, VS Code

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • academic-search-mcp-server by afrise · ⭐ 119

    Academic Paper Search MCP Server for Claude Desktop integration. Allows Claude to access data from Semantic Sc

  • pluggedin-app by VeriTeknik · ⭐ 103

    The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and

  • mcp-python-interpreter by yzfly · ⭐ 102

    MCP Python Interpreter: run python code. Python-mcp-server, mcp-python-server, Code Executor

  • vision-memory-mcp by putervision · ⭐ 69

    Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vect

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is brave-api?

brave-api is Brave API is totally free. No login. No API key. No bullshit.. It is categorized as a MCP Server with 51 GitHub stars.

What programming language is brave-api written in?

brave-api is primarily written in Python. It covers topics such as brave, brave-api, brave-ask.

How do I install or use brave-api?

You can find installation instructions and usage details in the brave-api GitHub repository at github.com/iqbalmh18/brave-api. The project has 51 stars and 11 forks, indicating an active community.

What license does brave-api use?

brave-api is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to brave-api?

The top alternatives to brave-api on Agent Skills Hub include MCP-Defender, claude-historian-mcp, academic-search-mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools