Agent Score 14.89 (#1 of 8). Fastest latency (669ms). Top-4 cluster statistically indistinguishable but Brave-Tavily gap (~1pt) is 'meaningful, not random.'
Brave Search API
activeIndependent web search API with own 40B-page index. #1 on AIMultiple 2026 Agentic Search Benchmark. 6-tool MCP server, SOC 2 Type II, 669ms latency.

Where it wins
Independent index (40B pages) — only independent commercial search API after Bing API shutdown (Aug 2025)
Fastest latency in independent benchmark (669ms)
6-tool MCP server (web, local, image, video, news, summarizer)
SOC 2 Type II attested (Oct 2025)
35K+ free customers, 2,700+ paid subscribers, billions of weekly API calls
Free tier (2K queries/month) lowers adoption barrier
22 platform integrations including Snowflake, AWS, Cursor, Windsurf
Where to be skeptical
Less semantic depth than Exa on conceptual/research queries
No dedicated SDK — users hit REST directly (smallest SDK download count)
No deep research endpoint — pure search only
MCP server stars (799) lag Exa (4,031) and Firecrawl (5,809)
Editorial verdict
#1 search API for AI agents — fastest latency (669ms), highest independent benchmark score (14.89), SOC 2 Type II attested. Default recommendation for general-purpose agent search.
Source
Videos
Reviews, tutorials, and comparisons from the community.
OpenClaw is taking over AI
OpenClaw Full Tutorial: 100% FREE Setup (AWS + OpenRouter + Free GLM Model) - 0$ monthly cost
Clawdbot is the best AI Agent I’ve ever built & here is how to run it for $0!
Related

Crawl4AI
93Free, open-source web scraping (Apache-2.0). 62K stars, 6,353 forks (nearly matches Firecrawl), actively maintained (v0.8.5, 2026-03-18), 384K weekly PyPI downloads. Best open-source alternative to Firecrawl.

SearXNG
88Privacy-first, self-hosted meta-search engine aggregating 70+ upstream engines. Zero cost, zero API keys, full data sovereignty.
Exa MCP Server
87Official Exa MCP for fast web search and crawling when the workflow is search-first rather than page-ops-first.
ScrapeGraphAI
82LLM-graph-based web scraper — describe what you want, AI builds the extraction graph. 23K stars, 194 HN pts, active development (v1.74.0, Mar 2026). Open-source + hosted API.
Public evidence
SOC 2 Type II attested. Only search API in category with this level of security certification.
2,700+ paid customers, 35K+ total API customers. Integrations include Snowflake, AWS, Cursor, Windsurf — strong enterprise signal.
Active MCP server with 6 tools. Strong npm downloads despite lower star count vs Exa/Firecrawl MCP servers.
Second independent source confirming Brave 14.89 vs Tavily 13.67 gap 'held up across repeated statistical tests.' Corroborates AIMultiple findings.
Microsoft shut down Bing API (Aug 2025) — Brave is now only independent commercial search API at scale. 200K+ developers signed up via OpenClaw release.
Independent developer choosing Brave API as backend for new search engine. Organic developer adoption signal.
New Place Search endpoint for map applications. Snowflake integration and AWS Marketplace listing in Feb 2026. Steady feature expansion.
Raw GitHub source
GitHub README peek
Constrained peek so you can sanity-check the source material without leaving the site.
Brave Search MCP Server
An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, image search, video search, news search, and AI-powered summarization. This project supports both STDIO and HTTP transports, with STDIO as the default mode.
Migration
1.x to 2.x
Default transport now STDIO
To follow established MCP conventions, the server now defaults to STDIO. If you would like to continue using HTTP, you will need to set the BRAVE_MCP_TRANSPORT environment variable to http, or provide the runtime argument --transport http when launching the server.
Response structure of brave_image_search
Version 1.x of the MCP server would return base64-encoded image data along with image URLs. This dramatically slowed down the response, as well as consumed unnecessarily context in the session. Version 2.x removes the base64-encoded data, and returns a response object that more closely reflects the original Brave Search API response. The updated output schema is defined in src/tools/images/schemas/output.ts.
Tools
Web Search (brave_web_search)
Performs comprehensive web searches with rich result types and advanced filtering options.
Parameters:
query(string, required): Search terms (max 400 chars, 50 words)country(string, optional): Country code (default: "US")search_lang(string, optional): Search language (default: "en")ui_lang(string, optional): UI language (default: "en-US")count(number, optional): Results per page (1-20, default: 10)offset(number, optional): Pagination offset (max 9, default: 0)safesearch(string, optional): Content filtering ("off", "moderate", "strict", default: "moderate")freshness(string, optional): Time filter ("pd", "pw", "pm", "py", or date range)text_decorations(boolean, optional): Include highlighting markers (default: true)spellcheck(boolean, optional): Enable spell checking (default: true)result_filter(array, optional): Filter result types (default: ["web", "query"])goggles(array, optional): Custom re-ranking definitionsunits(string, optional): Measurement units ("metric" or "imperial")extra_snippets(boolean, optional): Get additional excerpts (Pro plans only)summary(boolean, optional): Enable summary key generation for AI summarization
Local Search (brave_local_search)
Searches for local businesses and places with detailed information including ratings, hours, and AI-generated descriptions.
Parameters:
- Same as
brave_web_searchwith automatic location filtering - Automatically includes "web" and "locations" in result_filter
Note: Requires Pro plan for full local search capabilities. Falls back to web search otherwise.
Video Search (brave_video_search)
Searches for videos with comprehensive metadata and thumbnail information.
Parameters:
query(string, required): Search terms (max 400 chars, 50 words)country(string, optional): Country code (default: "US")search_lang(string, optional): Search language (default: "en")ui_lang(string, optional): UI language (default: "en-US")count(number, optional): Results per page (1-50, default: 20)offset(number, optional): Pagination offset (max 9, default: 0)spellcheck(boolean, optional): Enable spell checking (default: true)safesearch(string, optional): Content filtering ("off", "moderate", "strict", default: "moderate")freshness(string, optional): Time filter ("pd", "pw", "pm", "py", or date range)
Image Search (brave_image_search)
Searches for images with automatic fetching and base64 encoding for direct display.
Parameters:
query(string, required): Search terms (max 400 chars, 50 words)country(string, optional): Country code (default: "US")search_lang(string, optional): Search language (default: "en")count(number, optional): Results per page (1-200, default: 50)safesearch(string, optional): Content filtering ("off", "strict", default: "strict")spellcheck(boolean, optional): Enable spell checking (default: true)
News Search (brave_news_search)
Searches for current news articles with freshness controls and breaking news indicators.
Parameters:
query(string, required): Search terms (max 400 chars, 50 words)country(string, optional): Country code (default: "US")search_lang(string, optional): Search language (default: "en")ui_lang(string, optional): UI language (default: "en-US")count(number, optional): Results per page (1-50, default: 20)offset(number, optional): Pagination offset (max 9, default: 0)spellcheck(boolean, optional): Enable spell checking (default: true)safesearch(string, optional): Content filtering ("off", "moderate", "strict", default: "moderate")freshness(string, optional): Time filter (default: "pd" for last 24 hours)extra_snippets(boolean, optional): Get additional excerpts (Pro plans only)goggles(array, optional): Custom re-ranking definitions
Summarizer Search (brave_summarizer)
Generates AI-powered summaries from web search results using Brave's summarization API.
Parameters:
key(string, required): Summary key from web search results (usesummary: truein web search)entity_info(boolean, optional): Include entity information (default: false)inline_references(boolean, optional): Add source URL references (default: false)
Usage: First perform a web search with summary: true, then use the returned summary key with this tool.
Configuration
Getting an API Key
- Sign up for a Brave Search API account
- Choose a plan:
- Search: The real-time search data your chatbots & agents need to generate answers. Complete search results (URLs, text, news, images, and more), with additional LLM context optimized for AI.
- Answers: Summarized, completed answers to any question. Answers grounded on a single search or multiple searches for better accuracy & reduced hallucinations.
- Generate your API key from the developer dashboard
Environment Variables
The server supports the following environment variables:
BRAVE_API_KEY: Your Brave Search API key (required)BRAVE_MCP_TRANSPORT: Transport mode ("http" or "stdio", default: "stdio")BRAVE_MCP_PORT: HTTP server port (default: 8000)BRAVE_MCP_HOST: HTTP server host (default: "0.0.0.0")BRAVE_MCP_LOG_LEVEL: Desired logging level("debug", "info", "notice", "warning", "error", "critical", "alert", or "emergency", default: "info")BRAVE_MCP_ENABLED_TOOLS: When used, specifies a whitelist for supported toolsBRAVE_MCP_DISABLED_TOOLS: When used, specifies a blacklist for supported toolsBRAVE_MCP_STATELESS: HTTP stateless mode (default: "true"). When running on Amazon Bedrock Agentcore, set to "true".
Command Line Options
node dist/index.js [options]
Options:
--brave-api-key <string> Brave API key
--transport <stdio|http> Transport type (default: stdio)
--port <number> HTTP server port (default: 8080)
--host <string> HTTP server host (default: 0.0.0.0)
--logging-level <string> Desired logging level (one of _debug_, _info_, _notice_, _warning_, _error_, _critical_, _alert_, or _emergency_)
--enabled-tools Tools whitelist (only the specified tools will be enabled)
--disabled-tools Tools blacklist (included tools will be disabled)
--stateless <boolean> HTTP Stateless flag