Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
ratacat avatar

Brave Search

  • 268 installs
  • 49 repo stars
  • Updated February 11, 2026
  • ratacat/claude-skills

Query Brave Search from agent workflows for privacy-oriented web retrieval when researching topics, APIs, vendors, or recent announcements.

About

Claude skill for integrating Brave Search into agent and automation workflows, enabling privacy-focused web retrieval for research, vendor evaluation, API discovery, and current-event fact gathering during early exploration.

  • Brave Search API integration patterns
  • Privacy-oriented web retrieval
  • Agent-friendly query workflows
  • Vendor and API discovery support
  • Timely announcement and doc lookup

Brave Search by the numbers

  • 268 all-time installs (skills.sh)
  • Ranked #2,414 of 16,556 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ratacat/claude-skills --skill brave-search

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs268
repo stars49
Last updatedFebruary 11, 2026
Repositoryratacat/claude-skills

What it does

Query Brave Search from agent workflows for privacy-oriented web retrieval when researching topics, APIs, vendors, or recent announcements.

Files

SKILL.mdMarkdownGitHub ↗

Brave Search API

Overview

Search the web, images, and news using Brave's privacy-focused Search API. Also supports AI Grounding for cited answers via OpenAI SDK compatibility.

Prerequisites

API Key required. Get one at https://api-dashboard.search.brave.com

export BRAVE_API_KEY="your-api-key"

Free tier: 2,000 queries/month. Pro plans unlock Local POI search and AI Grounding.

When to Use

  • Searching the web for current information
  • Finding images on a topic
  • Getting recent news articles
  • AI-grounded answers with citations
  • Autocomplete suggestions
  • Location/POI searches (Pro plan)

High-Throughput Usage

Go wide, go fast. This API supports high concurrency—up to 50 requests/second. Don't hold back:

  • Fire searches in parallel. Need to research 10 different topics? Launch 10 searches simultaneously. Use multiple Bash tool calls in a single message.
  • Use subagents for heavy results. When expecting lots of context (many results, extra snippets, research mode), dispatch a subagent to run the search and synthesize findings. This preserves your main context window.
  • Batch related queries. Searching for competitors, alternatives, or multiple aspects of a topic? Run them all at once.
digraph parallel_search {
    rankdir=LR;
    node [shape=box];

    task [label="Research task"];
    q1 [label="Query 1"];
    q2 [label="Query 2"];
    q3 [label="Query 3"];
    subagent [label="Subagent\n(preserves context)"];
    synthesize [label="Synthesized\nfindings"];

    task -> q1;
    task -> q2;
    task -> q3;
    q1 -> subagent [style=dashed];
    q2 -> subagent [style=dashed];
    q3 -> subagent [style=dashed];
    subagent -> synthesize;
}

When to use subagents:

  • Searching for many sources on a topic (launch search subagent, return summary)
  • Deep research with AI Grounding (high token usage, let subagent handle)
  • Comparing multiple options (run parallel searches, subagent synthesizes)

When to search directly:

  • Quick single queries where you need the raw URLs/snippets
  • Low result counts where context isn't a concern

Quick Reference

TaskCommand
Web searchbrave-search web "query"
Image searchbrave-search images "query"
News searchbrave-search news "query"
AI answerbrave-search ai "question"
Suggestionsbrave-search suggest "partial query"
Check keybrave-search check-key

API Endpoints

APIEndpointPlan
Web Search/res/v1/web/searchFree
Image Search/res/v1/images/searchFree
News Search/res/v1/news/searchFree
Suggest/res/v1/suggest/searchFree
AI Grounding/res/v1/chat/completionsAI Grounding
Local POI/res/v1/local/poisPro
Summarizer/res/v1/summarizer/searchPro

Common Parameters

Web Search

# Basic search
brave-search web "python async tutorial" --count 10

# Filter by freshness (pd=24h, pw=7d, pm=31d, py=365d)
brave-search web "latest news" --freshness pd

# Filter by country and language
brave-search web "local restaurants" --country US --lang en

# Safe search (off, moderate, strict)
brave-search web "query" --safesearch strict

# Get extra snippets
brave-search web "query" --extra-snippets

# Filter result types (web, news, videos, images, discussions)
brave-search web "query" --filter web,news

Image Search

# Basic image search
brave-search images "mountain sunset"

# With safe search
brave-search images "landscape" --safesearch strict --count 20

News Search

# Recent news
brave-search news "AI developments" --count 10

# News with freshness filter
brave-search news "election results" --freshness pd

AI Grounding (Cited Answers)

# Get an AI answer with citations
brave-search ai "What is the tallest building in the world?"

# Enable deep research (multiple searches, slower)
brave-search ai "Compare React and Vue in 2024" --research

Workflow

digraph brave_search {
    rankdir=TB;
    node [shape=box];

    need [label="What do you need?" shape=diamond];
    web [label="Web Search\nbrave.py web"];
    images [label="Image Search\nbrave.py images"];
    news [label="News Search\nbrave.py news"];
    ai [label="AI Answer\nbrave.py ai"];

    results [label="Parse JSON results"];
    cite [label="Include citations\nfor AI answers"];

    need -> web [label="web pages"];
    need -> images [label="images"];
    need -> news [label="recent news"];
    need -> ai [label="cited answer"];

    web -> results;
    images -> results;
    news -> results;
    ai -> cite;
}

Response Structure

Web Search Results

{
  "web": {
    "results": [
      {
        "title": "Page Title",
        "url": "https://example.com",
        "description": "Snippet from the page...",
        "extra_snippets": ["Additional context..."]
      }
    ]
  },
  "query": {
    "original": "search query",
    "altered": "modified query if spellchecked"
  }
}

AI Grounding Response

Returns OpenAI-compatible format with inline citations:

The tallest building is the Burj Khalifa[1] at 828 meters...

[1] https://source-url.com

Common Options

OptionValuesDescription
--count1-20 (web), 1-200 (images)Number of results
--countryUS, GB, DE, FR, etc.Search region
--langen, de, fr, es, etc.Search language
--safesearchoff, moderate, strictAdult content filter
--freshnesspd, pw, pm, pyTime filter
--jsonflagOutput raw JSON

Error Handling

ErrorCauseFix
401 UnauthorizedInvalid/missing API keyCheck BRAVE_API_KEY
429 Rate LimitedToo many requestsWait or upgrade plan
422 ValidationInvalid parametersCheck parameter values

Rate Limits

  • Free: 1 req/sec, 2,000/month
  • Pro: Higher limits, check dashboard
  • Response headers show remaining quota: X-RateLimit-Remaining

Common Mistakes

MistakeFix
API key not setexport BRAVE_API_KEY="..."
Wrong endpoint for planCheck subscription at dashboard
Too many resultsWeb max is 20, use offset for pagination
No AI groundingRequires AI Grounding subscription

Related skills

AI & Agent Buildingresearchautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.