brave-search-setupConfigure Brave Search API and troubleshoot network/proxy issues for web_search functionality. Use when user needs to (1) Set up Brave Search API key, (2) Fix web_search fetch failures, (3) Configure proxy for OpenClaw tools on macOS with Clash/V2Ray/Surge, or (4) Diagnose "fetch failed" errors with web_search/web_fetch tools.
Install via ClawdBot CLI:
clawdbot install qingliu1617-art/brave-search-setupSetup Brave Search API and resolve network connectivity issues for OpenClaw web tools.
# Option A: Via config.patch (key will be stored securely)
openclaw gateway config.patch --raw '{"tools":{"web":{"search":{"apiKey":"YOUR_BRAVE_API_KEY","enabled":true,"provider":"brave"}}}}'
Or edit ~/.openclaw/openclaw.json directly:
{
"tools": {
"web": {
"search": {
"enabled": true,
"provider": "brave",
"apiKey": "YOUR_BRAVE_API_KEY"
}
}
}
}
openclaw web.search --query "test" --count 1
If works → Done.
If "fetch failed" → Continue to proxy setup.
Common proxy ports by client:
Detect actual port:
# Check if Clash is running
ps aux | grep -i clash
# Find mixed-port from Clash config
cat "~/Library/Application Support/io.github.clash-verge-rev.clash-verge-rev/clash-verge.yaml" | grep mixed-port
# Or test common ports
for port in 7890 7891 7897 6152 6153 1080 10808; do
if nc -z 127.0.0.1 $port 2>/dev/null; then
echo "Port $port is open"
fi
done
Method A: launchctl (Recommended - survives restart)
# Set for current session and future sessions
launchctl setenv HTTPS_PROXY http://127.0.0.1:7897
launchctl setenv HTTP_PROXY http://127.0.0.1:7897
Method B: Shell export (Session only)
export HTTPS_PROXY=http://127.0.0.1:7897
export HTTP_PROXY=http://127.0.0.1:7897
Method C: Add to shell profile (Permanent)
echo 'export HTTPS_PROXY=http://127.0.0.1:7897' >> ~/.zshrc
echo 'export HTTP_PROXY=http://127.0.0.1:7897' >> ~/.zshrc
source ~/.zshrc
openclaw gateway config.patch --raw '{"commands":{"restart":true}}'
# Restart to pick up proxy env vars
openclaw gateway restart
# Or use SIGUSR1
kill -USR1 $(pgrep -f "openclaw gateway")
# Test web search
openclaw web.search --query "Brave Search test" --count 1
# Test web fetch
openclaw web.fetch --url "https://api.search.brave.com" --max-chars 100
Symptom: Browser can access Google, but OpenClaw tools fail.
Cause: Gateway process started before proxy env vars were set.
Solution: Restart Gateway after setting HTTPS_PROXY.
Enable restart command:
openclaw gateway config.patch --raw '{"commands":{"restart":true}}'
Verify key is set:
openclaw gateway config.get | grep -A5 'web.*search'
Test directly with curl:
curl -s "https://api.search.brave.com/res/v1/web/search?q=test&count=1" \
-H "Accept: application/json" \
-H "X-Subscription-Token: YOUR_API_KEY"
Clash "mixed-port" (default 7897) handles both HTTP and SOCKS5.
If using dedicated ports:
Not all tools respect HTTPS_PROXY. For tools that don't:
# Use proxychains-ng
brew install proxychains-ng
# Configure
sudo tee /usr/local/etc/proxychains.conf <<EOF
strict_chain
proxy_dns
[ProxyList]
http 127.0.0.1 7897
EOF
# Run with proxy
proxychains4 openclaw web.search --query "test"
config.patch or edit JSONlaunchctl setenv or shell exportopenclaw gateway restartGenerated Mar 1, 2026
Startups can use this skill to configure Brave Search API for gathering competitive intelligence and market trends via web searches. It ensures reliable data fetching even in restricted network environments, enabling teams to access global information without interruptions.
Researchers in academia can set up Brave Search with proxy support to access international scholarly articles and datasets. This skill helps bypass network restrictions, ensuring continuous access to web resources for literature reviews and data collection.
Content creators and SEO specialists can leverage this skill to perform web searches for keyword research and competitor analysis. By configuring the API and proxy, they ensure stable connectivity to fetch search results and optimize content strategies effectively.
Security analysts can use this skill to set up Brave Search for monitoring online threats and gathering intelligence from web sources. Proxy configuration ensures secure and uninterrupted data fetching from potentially blocked or sensitive domains.
E-commerce businesses can configure Brave Search to scout for suppliers and product trends globally. The skill's proxy setup allows access to international websites, facilitating efficient web searches for sourcing and market analysis.
Offer this skill as part of a subscription-based AI tool suite for businesses needing reliable web search capabilities. Revenue comes from monthly or annual fees, with tiered pricing based on API usage and support levels.
Provide consulting services to help organizations set up and troubleshoot Brave Search API and proxy configurations. Revenue is generated through project-based fees or hourly rates for customization and ongoing maintenance.
Release a free version of this skill for basic setup, with premium features like advanced proxy management and priority support. Revenue is driven by upgrades to premium plans and add-ons for enterprise users.
💬 Integration Tip
Ensure the Brave Search API key is securely stored and regularly updated in the configuration. For proxy setups, verify the correct port and environment variables to avoid fetch failures in production environments.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.