Brave Search MCP Server | MewCP

Documentation

Guide

Search the web, images, videos, news, and local places through Brave's independent index — plus AI summarization and RAG-ready context extraction.

A Model Context Protocol (MCP) server that exposes the Brave Search API's search endpoints for web, local, video, image, news, and place search, along with AI summarization and LLM-context extraction.

Overview

The Brave Search MCP Server provides:

Comprehensive web search with rich metadata — results can include FAQ, Discussions, News, and Video items alongside standard web results
Local business and points-of-interest (POI) search with ratings, addresses, phone numbers, hours, and AI descriptions, with a graceful fallback to web results when enriched local data isn't available
Dedicated video, image, and news search endpoints
A structured place-search endpoint for POI data anchored to a location or lat/long coordinates
AI-generated summarization of web search results via Brave's Summarizer API
Pre-extracted, relevance-ranked web content via Brave's LLM Context API — actual page substance (text chunks, tables, code blocks) rather than just links and snippets

Perfect for:

AI agents that need general-purpose web search grounded in an independent search index
Local business lookup and "near me" style assistants
News monitoring and current-events tools
Media search integrations (images, videos)
RAG pipelines that need pre-extracted, relevance-ranked web content for grounding
Quickly summarizing a set of search results into an AI-generated answer

Tools

Help Improve This Server

Missing a tool?

Found a bug?

Have an idea for an improvement?

Share your feedback directly with the maintainers - every feedback helps make this server better for everyone.

Open GitHub Issues →

- `query` (string, required) — Search query (max 400 chars, 50 words)
- `country` (CountryCode, optional, default: "US") — Country for results
- `search_lang` (SearchLang, optional, default: "en") — Search language
- `ui_lang` (UiLang, optional, default: "en-US") — UI language
- `count` (int, optional, default: 10) — Number of web results (1–20)
- `offset` (int, optional, default: 0) — Pagination offset (0–9)
- `safesearch` (SafeSearch, optional, default: "moderate") — Safe-search level
- `freshness` (string, optional) — Time filter: pd (day) pw (week) pm (month) py (year) or YYYY-MM-DDtoYYYY-MM-DD
- `text_decorations` (bool, optional, default: true) — Include decoration markers in snippets
- `spellcheck` (bool, optional, default: true) — Spellcheck the query
- `result_filter` (list of ResultFilter, optional) — Subset of result types to return (default ['web','query'])
- `goggles` (list of string, optional) — Goggle HTTPS URLs for custom re-ranking
- `units` (Units, optional) — Measurement units
- `extra_snippets` (bool, optional) — Up to 5 extra excerpts per result (Pro plan)
- `summary` (bool, optional) — Return a summarizer_key to pass to summarize_search_results

{
  results: {
    summarizer_key: string | null;
    url: string | null;
    title: string | null;
    description: string | null;
    extra_snippets: string[] | null;
    question: string | null;
    answer: string | null;
    mutated_by_goggles: boolean | null;
    data: string | null;       // discussion body
    source: Record<string, unknown> | null;
    breaking: boolean | null;
    is_live: boolean | null;
    age: string | null;
    thumbnail_url: string | null;
    duration: string | null;
    view_count: number | null;
    creator: string | null;
    publisher: string | null;
    tags: string[] | null;
  }[];
}

Searches for local businesses and places via the Brave Search API. Returns ratings, addresses, phone numbers, hours, and AI descriptions.

Access to enriched POI data requires a Brave Search API Pro plan; the tool gracefully falls back to web results if local data is unavailable.

Inputs:

- `query` (string, required) — Local search query, e.g. 'pizza near downtown Chicago'
- `count` (int, optional, default: 5) — Results to return (1–20)
- `country` (CountryCode, optional, default: "US") — Country code

output data schema:

{
  results: {
    // POI-shaped fields
    name: string | null;
    address: string | null;
    phone: string | null;
    rating: number | null;
    review_count: number | null;
    hours: unknown[] | null;
    price_range: string | null;
    categories: string[]

Searches for videos via the Brave Search API. Returns titles, URLs, durations, view counts, creators, and thumbnails.

Inputs:

- `query` (string, required) — Video search query (max 400 chars, 50 words)
- `country` (CountryCode, optional, default: "US") — Country for results
- `search_lang` (SearchLang, optional, default: "en") — Search language
- `ui_lang` (UiLang, optional, default: "en-US") — UI language
- `count` (int, optional, default: 10) — Results to return (1–20)
- `offset` (int, optional, default: 0) — Pagination offset (0–9)
- `safesearch` (SafeSearch, optional, default: "moderate") — Safe-search level
- `freshness` (string, optional) — Time filter: pd pw pm py or YYYY-MM-DDtoYYYY-MM-DD
- `spellcheck` (bool, optional, default: true) — Spellcheck the query

output data schema:

{
  results: {
    url: string | null;
    title: string | null;
    description: string | null;
    age: string | null;
    thumbnail_url: string | null;
    duration: string | null;

Searches for images via the Brave Search API. Returns direct image URLs, source pages, and dimensions. Images are returned as URLs — no base64 encoding.

Inputs:

- `query` (string, required) — Image search query (max 400 chars, 50 words)
- `country` (CountryCode, optional, default: "US") — Country for results
- `search_lang` (SearchLang, optional, default: "en") — Search language
- `count` (int, optional, default: 10) — Results to return (1–20)
- `safesearch` (SafeSearch, optional, default: "moderate") — Safe-search level
- `spellcheck` (bool, optional, default: true) — Spellcheck the query

output data schema:

{
  results: {
    url: string | null;
    source: string | null;
    title: string | null;
    width: number | null;
    height: number | null;
    format: string | null;

Searches for current news articles via the Brave Search API. Returns headlines, sources, publication age, and descriptions.

Inputs:

- `query` (string, required) — News search query (max 400 chars, 50 words)
- `country` (CountryCode, optional, default: "US") — Country for results
- `search_lang` (SearchLang, optional, default: "en") — Search language
- `ui_lang` (UiLang, optional, default: "en-US") — UI language
- `count` (int, optional, default: 10) — Results to return (1–20)
- `offset` (int, optional, default: 0) — Pagination offset (0–9)
- `safesearch` (SafeSearch, optional, default: "moderate") — Safe-search level
- `freshness` (string, optional) — Time filter: pd pw pm py or YYYY-MM-DDtoYYYY-MM-DD
- `extra_snippets` (bool, optional) — Up to 5 extra excerpts per result (Pro plan)
- `spellcheck` (bool, optional, default: true) — Spellcheck the query

output data schema:

{
  results: {
    mutated_by_goggles: boolean | null;
    source: Record<string, unknown> | null;
    breaking: boolean | null;
    is_live: boolean | null;
    age: string | null;
    url: string

Retrieves points of interest (POIs) with structured business data via Brave's dedicated place-search endpoint. Returns addresses, hours, ratings, categories, and contact info.

Geographic context is required — provide latitude/longitude or a location string (e.g. 'san francisco ca united states').

Access requires a Brave Search API Pro plan.

Inputs:

- `query` (string, required) — Search query — shapes result type, e.g. 'coffee shops' or 'Eiffel Tower'
- `location` (string, optional) — Location context, e.g. 'san francisco ca united states' or 'tokyo japan'
- `latitude` (float, optional) — Latitude (-90 to 90)
- `longitude` (float, optional) — Longitude (-180 to 180)
- `radius` (int, optional) — Proximity bias in metres (not a hard cutoff)
- `count` (int, optional, default: 20) — Results to return (1–50)
- `country` (CountryCode, optional, default: "US") — Country code
- `search_lang` (SearchLang, optional, default: "en") — Search language
- `ui_lang` (UiLang, optional, default: "en-US") — UI language
- `units` (Units, optional) — Measurement units
- `safesearch` (SafeSearch, optional, default: "moderate") — Safe-search level
- `spellcheck` (bool, optional, default: true) — Spellcheck the query

output data schema:

{
  results: {
    name: string | null;
    address: string | null;
    phone: string | null;
    rating: number | null;
    review_count: number | null;
    hours: unknown[] | null;

Retrieves an AI-generated summary of web search results using Brave's Summarizer API.

Workflow: call search_web with summary=true first, then pass the returned summarizer_key to this tool.

Requires a Brave Search API Pro AI subscription.

Inputs:

- `key` (string, required) — Summarizer key from search_web called with summary=true
- `entity_info` (bool, optional, default: false) — Include related entity information

output data schema:

{
  text: string;
}

Retrieves pre-extracted, relevance-ranked web content using Brave's LLM Context API, optimised for AI agents, LLM grounding, and RAG pipelines.

Unlike a web search (links + short descriptions), this tool returns the actual substance of matching pages — text chunks, tables, code blocks — so the model can reason over it directly.

When to use:

Grounding answers in fresh, relevant web content (RAG)
Question answering and fact-checking against current sources
Gathering source material without manually fetching pages

When relaying results in markdown environments, cite source URLs from the 'sources' map.

Inputs:

- `query` (string, required) — Search query (max 400 chars, 50 words)
- `country` (CountryCode, optional, default: "US") — Country for results
- `search_lang` (SearchLang, optional, default: "en") — Search language
- `count` (int, optional, default: 20) — Number of results to consider (1–50)
- `freshness` (string, optional) — Time filter: pd pw pm py or YYYY-MM-DDtoYYYY-MM-DD
- `spellcheck` (bool, optional, default: true) — Spellcheck the query
- `maximum_number_of_urls` (int, optional) — Max URLs to extract content from (1–50)
- `maximum_number_of_tokens` (int, optional) — Total token budget (1024–32768)
- `maximum_number_of_snippets` (int, optional) — Max snippets across all URLs (1–256)
- `context_threshold_mode` (ContextThresholdMode, optional) — Relevance filtering mode
- `maximum_number_of_tokens_per_url` (int, optional) — Per-URL token budget (512–8192)
- `maximum_number_of_snippets_per_url` (int, optional) — Per-URL snippet cap (1–100)
- `enable_local` (bool, optional) — Enable local recall
- `enable_source_metadata` (bool, optional) — Enrich source metadata
- `x_loc_lat` (float, optional) — User latitude (-90 to 90)
- `x_loc_long` (float, optional) — User longitude (-180 to 180)
- `x_loc_city` (string, optional) — User city
- `x_loc_country` (string, optional) — User 2-letter country code

output data schema:

{
  // This model declares no fixed fields of its own — the entire response
  // shape is the passthrough JSON from Brave's LLM Context API. The tool
  // description references a `sources` map for citing result URLs.
  [key: string]: unknown;
}

Every tool returns the same top-level envelope. Only data varies per tool.

// Success
{
  "success": true,
  "statusCode": 200,
  "retriable": false,
  "retry_after_seconds": null,
  "error": null,
  "data": { ... }
}
 
// Error
{
  "success": false,
  "statusCode": 400,
  "retriable": false,
  "retry_after_seconds": null,
  "error": { "code": "{ERROR_CODE}", "message": "{description}", "details": {} },
  "data": null
}

retriable — true when it is safe to retry (rate limit, network error, 503). false for validation and auth errors.
retry_after_seconds — seconds to wait before retrying; present only when retriable is true and the upstream specifies a delay.
error.code — machine-readable string: VALIDATION_ERROR, AUTH_ERROR, UPSTREAM_ERROR, SERVER_ERROR.
All models accept additional, undocumented fields beyond what's listed above () — Brave may add fields to its API responses that aren't reflected in these schemas yet.

data

Brave Search

Documentation

Overview

Tools

Help Improve This Server

Overview

Tools

API Parameters Reference

Getting Your Brave Search API Key

Troubleshooting