Skip to content

How Brave Search API’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score31/100

Agent-ready 40.8 × 0.30 = 12.24

API quality 6.0 × 0.20 = 1.20

Openness 18.0 × 0.20 = 3.60

Built-in AI 75.0 × 0.15 = 11.25

Automation 18.0 × 0.15 = 2.70

(12.24 + 1.20 + 3.60 + 11.25 + 2.70) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 30.99 ÷ 1.00 = 31.0

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready40.8/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [probe] https://api-dashboard.search.brave.com/llms.txtPROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for developers: web, image, video and news search, plus LLM-read
  • [claimed-docs] https://api-dashboard.search.brave.com/documentation/resources/skills/index.html.mdSkills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverAn MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, place search, image search, video search, news search, LLM context, and AI-powered summarization.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedLooking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consumption, and benchmarked as the most powerful Search API for AI.
  • [probe] https://api-dashboard.search.brave.com/app/documentation.mdPROBE docs-md: HTTP 404 at https://api-dashboard.search.brave.com/app/documentation.md

Run the product headlessly / in CI for automationweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationGet your API key and make your first request in minutes.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedTo fetch AI-generated descriptions for locations: curl "https://api.search.brave.com/res/v1/local/descriptions?ids=..."
  • [claimed-docs] https://brave.com/search/api/guides/This guide covers the steps to enable Brave Search via the official Brave Search community node in n8n.io, a flexible and community-driven automation platform.
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverAn MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, place search, image search, video search, news search, LLM context, and AI-powered summarization.
  • [claimed-docs] https://brave.com/search/api/guides/This guide will help you get set up with the Brave Search API in Dify, an open-source platform designed to simplify AI application development, and offer real-time, accurate search results as part of AI agent orchestration.
  • [probe] https://github.com/brave/brave-search-mcp-serverofficial MCP server documented at https://github.com/brave/brave-search-mcp-server

Plug MCP servers into this product so it can use their toolsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 3

3 (weight) × 7 (quality) × 0.6 (partial) = 12.6 of 30 max

  • [claimed-docs] https://brave.com/search/api/guides/This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol (MCP).
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverAn MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, place search, image search, video search, news search, LLM context, and AI-powered summarization.
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverGenerates AI-powered summaries from web search results using Brave's summarization API...First perform a web search with `summary: true`, then use the returned summary key with this tool.
  • [probe] https://github.com/brave/brave-search-mcp-serverofficial MCP server documented at https://github.com/brave/brave-search-mcp-server
  • [community] https://news.ycombinator.com/item?id=46822822User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since guides show people integrating it with AI agents like OpenClaw despite this restriction.
  • [community] https://news.ycombinator.com/item?id=46822822Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign up for the AI-specific plan instead to comply with ToS.

Use an official CLIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationGet your API key and make your first request in minutes.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationAdvanced Web search, with pre-extracted content that's optimized for AI agents, LLM grounding, and RAG pipelines.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedLooking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consumption, and benchmarked as the most powerful Search API for AI.
  • [probe] https://api-dashboard.search.brave.com/llms.txtPROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for developers: web, image, video and news search, plus LLM-read
  • [probe] https://api-dashboard.search.brave.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.json, https://api-dashboard.search.brave.com/api/openapi.json, https://api-dashboard.search.brave.com/.well-known/openapi.json)
  • [community] https://news.ycombinator.com/item?id=46822822User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since guides show people integrating it with AI agents like OpenClaw despite this restriction.
  • [community] https://news.ycombinator.com/item?id=46822822Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign up for the AI-specific plan instead to comply with ToS.

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationGet your API key and make your first request in minutes.

Build against official SDKsweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverAn MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, place search, image search, video search, news search, LLM context, and AI-powered summarization.
  • [claimed-docs] https://api-dashboard.search.brave.com/documentation/services/answers/index.html.mdUse the familiar OpenAI SDK for seamless integration
  • [probe] https://api-dashboard.search.brave.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.json, https://api-dashboard.search.brave.com/api/openapi.json, https://api-dashboard.search.brave.com/.well-known/openapi.json)
  • [probe] https://github.com/brave/brave-search-mcp-serverofficial MCP server documented at https://github.com/brave/brave-search-mcp-server
  • [claimed-docs] https://api-dashboard.search.brave.com/documentation/resources/skills/index.html.mdSkills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 73.4 ÷ 180 × 100 = 40.8

API quality6.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/other/suggestions/index.html.mdIntelligent search suggestions to help users find what they’re looking for.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/web/rich_search/index.html.mdGets the rich realtime result for the requested resource, ie. query like `weather in london`.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/web/local_pois/index.html.mdGet detailed information about points of interest.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedLast 24 Hours (`pd`): Get the latest updates and recent content
  • [probe] https://api-dashboard.search.brave.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.json, https://api-dashboard.search.brave.com/api/openapi.json, https://api-dashboard.search.brave.com/.well-known/openapi.json)
  • [probe] https://api-dashboard.search.brave.com/app/documentation.mdPROBE docs-md: HTTP 404 at https://api-dashboard.search.brave.com/app/documentation.md

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://api-dashboard.search.brave.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.json, https://api-dashboard.search.brave.com/api/openapi.json, https://api-dashboard.search.brave.com/.well-known/openapi.json)
  • [probe] https://api-dashboard.search.brave.com/app/documentation.mdPROBE docs-md: HTTP 404 at https://api-dashboard.search.brave.com/app/documentation.md
  • [probe] https://api-dashboard.search.brave.com/llms.txtPROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for developers: web, image, video and news search, plus LLM-read

Test against a sandbox environment without touching production dataweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

API quality = 3.6 ÷ 60 × 100 = 6.0

Openness18.0/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedWeb Search supports Goggles, which allow you to apply custom re-ranking on top of search results. You can: Boost or demote specific websites and domains
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedTo fetch AI-generated descriptions for locations: curl "https://api.search.brave.com/res/v1/local/descriptions?ids=..."
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationAI-generated answers backed by real-time web search and verifiable sources.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationGet real-time news articles from thousands of trusted sources worldwide.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationSearch through billions of images with advanced filtering and SafeSearch options.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationFind video content from across the web with metadata and thumbnails.
  • [claimed-docs] https://api-dashboard.search.brave.com/documentation/index.html.mdFind geographic places — businesses, landmarks, POIs, cities, addresses, and more.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/other/suggestions/index.html.mdIntelligent search suggestions to help users find what they’re looking for.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/other/spell_check/index.html.mdIntelligent spell checking to improve query quality and help users find what they’re looking for.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/web/rich_search/index.html.mdGets the rich realtime result for the requested resource, ie. query like `weather in london`.
  • [community] https://news.ycombinator.com/item?id=46822822User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since guides show people integrating it with AI agents like OpenClaw despite this restriction.
  • [community] https://news.ycombinator.com/item?id=46822822Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign up for the AI-specific plan instead to comply with ToS.
  • [probe] https://api-dashboard.search.brave.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.json, https://api-dashboard.search.brave.com/api/openapi.json, https://api-dashboard.search.brave.com/.well-known/openapi.json)

Export all of my data in open formats and leaveweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Openness = 7.2 ÷ 40 × 100 = 18.0

Built-in AI75.0/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentationAI-generated answers backed by real-time web search and verifiable sources.
  • [claimed-docs] https://api-dashboard.search.brave.com/documentation/services/answers/index.html.mdAI-generated answers backed by real-time web search and verifiable sources
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverGenerates AI-powered summaries from web search results using Brave's summarization API...First perform a web search with `summary: true`, then use the returned summary key with this tool.
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverGenerates AI-powered summaries from web search results using Brave's summarization API.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedLooking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consumption, and benchmarked as the most powerful Search API for AI.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/web/poi_descriptions/index.html.mdGet LLM generated descriptions about points of interest.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/other/suggestions/index.html.mdIntelligent search suggestions to help users find what they’re looking for.
  • [community] https://news.ycombinator.com/item?id=46822822User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since guides show people integrating it with AI agents like OpenClaw despite this restriction.
  • [community] https://news.ycombinator.com/item?id=46822822Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign up for the AI-specific plan instead to comply with ToS.

Set up automations that run autonomously in the backgroundweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Delegate tasks to a built-in AI assistant inside the productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/web/rich_search/index.html.mdGets the rich realtime result for the requested resource, ie. query like `weather in london`.
  • [claimed-docs] https://api-dashboard.search.brave.com/documentation/resources/skills/index.html.mdSkills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code
  • [claimed-docs] https://brave.com/search/api/guides/This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol (MCP).
  • [claimed-docs] https://github.com/brave/brave-search-mcp-serverAn MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, place search, image search, video search, news search, LLM context, and AI-powered summarization.
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedLooking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consumption, and benchmarked as the most powerful Search API for AI.
  • [claimed-docs] https://brave.com/search/api/guides/This guide explains how to equip OpenClaw with better exposure to the Brave Search API, giving agents access to crucial context and enhanced Web search capabilities.
  • [claimed-docs] https://brave.com/search/api/guides/This guide will help you get set up with the Brave Search API in Dify, an open-source platform designed to simplify AI application development, and offer real-time, accurate search results as part of AI agent orchestration.
  • [community] https://news.ycombinator.com/item?id=46822822User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since guides show people integrating it with AI agents like OpenClaw despite this restriction.
  • [community] https://news.ycombinator.com/item?id=46822822Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign up for the AI-specific plan instead to comply with ToS.

Built-in AI = 30.0 ÷ 40 × 100 = 75.0

Automation18.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedUse the id values to fetch detailed POI information from the Local Search API endpoints. The ids query parameter accepts up to 20 location IDs
  • [claimed-docs] https://api-dashboard.search.brave.com/app/documentation/web-search/get-startedUse the `id` values to fetch detailed POI information from the Local Search API endpoints.
  • [claimed-docs] https://api-dashboard.search.brave.com/api-reference/web/local_pois/index.html.mdGet detailed information about points of interest.

Define rules that trigger actions automatically on eventsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 3.6 ÷ 20 × 100 = 18.0