mcpField
B
brave-search

brave-search

github.com/steipeteProductivity7.4k831 installsUpdated 1w ago
Repository

About brave-search

A headless web-search skill that uses Brave Search and extracts readable page content as Markdown. It is intended for research tasks that need search results or content from a specific URL without interactive browsing.

Key features

  1. 01Search the web with Brave Search
  2. 02Adjust the number of results
  3. 03Include page content in results
  4. 04Extract URL content as Markdown
  5. 05Requires BRAVE_API_KEY

Use cases

  1. 01Find documentation and API references
  2. 02Check facts and current information
  3. 03Retrieve readable content from a URL

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/steipete/agent-scripts --skill brave-search

After installing, type/brave-searchin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

.gitignore
content.js
package-lock.json
package.json
search.js

Details

From the project README

Brave Search

Headless web search and content extraction using Brave Search. No browser required.

Setup

Run once before first use:

cd ~/Projects/agent-scripts/skills/brave-search
npm ci

Needs env: BRAVE_API_KEY.

Search

./search.js "query"                    # Basic search (5 results)
./search.js "query" -n 10              # More results
./search.js "query" --content          # Include page content as markdown
./search.js "query" -n 3 --content     # Combined

Extract Page Content

./content.js https://example.com/article

Fetches a URL and extracts readable content as markdown.

Output Format

--- Result 1 ---
Title: Page Title
Link: https://example.com/page
Snippet: Description from search results
Content: (if --content flag used)
  Markdown content extracted from the page...

--- Result 2 ---
...

When to Use

  • Searching for documentation or API references
  • Looking up facts or current information
  • Fetching content from specific URLs
  • Any task requiring web search without interactive browsing

Comments

Markdown supported