Brave Search

Created By
modelcontextprotocol2 years ago
Web and local search using Brave's Search API
Overview

Brave Search is an MCP server implementation that utilizes the Brave Search API to provide both web and local search capabilities.

To use Brave Search, sign up for a Brave Search API account to get an API key, then configure the server in your application with the provided API key and start making search queries.

  • Web Search: Execute general queries, news, and articles with pagination and freshness controls.
  • Local Search: Find businesses and services with detailed descriptions, automatically falling back to web search if no local results are found.
  • Flexible Filtering: Control types of results, safety levels, and content freshness.
  • Smart Fallbacks: Automatically fallback to web search for local queries when no results are found.
  1. Conducting general web searches for news articles.
  2. Finding local businesses or services quickly.
  3. Custom filtering of search results based on user-defined criteria.
  • How do I obtain an API Key for Brave Search?

Sign up for a Brave Search API account, select a plan, and generate your API key from the developer dashboard.

  • Is there a free tier available?

Yes, the free tier allows up to 2,000 queries per month.

  • What happens if no local search results are found?

The service automatically falls back to a web search to continue providing relevant results.

Server Config

{
  "mcpServers": {
    "brave-search": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BRAVE_API_KEY",
        "mcp/brave-search"
      ],
      "env": {
        "BRAVE_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
Project Info
Hosted
Featured
Created At
2 years ago
Updated At
a year ago
Author Name
modelcontextprotocol
Star
-
Language
-
License
-

Recommend Servers

View All
Payai X402 Tools

6 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago