> **Building with AI coding agents?** If you're using an AI coding agent, install the official Scalekit plugin. It gives your agent full awareness of the Scalekit API — reducing hallucinations and enabling faster, more accurate code generation. > > - **Claude Code**: `/plugin marketplace add scalekit-inc/claude-code-authstack` then `/plugin install @scalekit-auth-stack` > - **GitHub Copilot CLI**: `copilot plugin marketplace add scalekit-inc/github-copilot-authstack` then `copilot plugin install @scalekit-auth-stack` > - **Codex**: run the bash installer, restart, then open Plugin Directory and enable `` > - **Skills CLI** (Windsurf, Cline, 40+ agents): `npx skills add scalekit-inc/skills --list` then `--skill ` > > `` / ``: `agent-auth`, `full-stack-auth`, `mcp-auth`, `modular-sso`, `modular-scim` — [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Brave Search
Connect to Brave Search to perform web, image, video, and news searches with privacy-focused results, plus AI-powered suggestions and spellcheck.
Brave Search logo
Supports authentication: API Key ## Tool list ## `brave_chat_completions` Get AI-generated answers grounded in real-time Brave Search results using an OpenAI-compatible chat completions interface. Returns summarized, cited answers with source references and token usage statistics. | Name | Type | Required | Description | | --- | --- | --- | --- | | `country` | string | No | Target country code for search results used to ground the answer (e.g., us, gb). | | `enable_citations` | boolean | No | Include inline citation markers in the response text. | | `enable_entities` | boolean | No | Include entity information (people, places, organizations) in the response. | | `enable_research` | boolean | No | Enable multi-search research mode for more comprehensive answers. | | `language` | string | No | Language code for the response (e.g., en, fr, de). | | `messages` | `array` | Yes | Array of conversation messages. Each message must have a 'role' (system, user, or assistant) and 'content' (string). | | `model` | string | No | The model to use. Must be 'brave' to use Brave's search-grounded AI model. | | `stream` | boolean | No | Whether to stream the response as server-sent events. | ## `brave_image_search` Search for images using Brave Search. Returns image results with thumbnails, source URLs, dimensions, and metadata. Supports filtering by country, language, and safe search. | Name | Type | Required | Description | | --- | --- | --- | --- | | `count` | integer | No | Number of image results to return (1–200). Defaults to 50. | | `country` | string | No | Country code for localised results (e.g., us, gb, de), or ALL for no restriction. | | `q` | string | Yes | The image search query string. | | `safesearch` | string | No | Safe search filter level. Defaults to strict (drops all adult content). | | `search_lang` | string | No | Language code for results (e.g., en, fr, de). | | `spellcheck` | boolean | No | Whether to enable spellcheck on the query. Defaults to true. | ## `brave_llm_context` Retrieve real-time web search results optimized as grounding context for LLMs. Returns curated snippets, source URLs, titles, and metadata specifically structured to maximize contextual relevance for AI-generated answers. Supports fine-grained token and snippet budgets. | Name | Type | Required | Description | | --- | --- | --- | --- | | `context_threshold_mode` | string | No | Relevance filter aggressiveness for snippet selection. Defaults to balanced. | | `count` | integer | No | Max number of search results to consider (1–50). Defaults to 20. | | `country` | string | No | Country code for localised results (e.g., us, gb, de). Defaults to us. | | `enable_local` | boolean | No | Enable location-aware recall for locally relevant results. | | `freshness` | string | No | Filter results by publish date: pd (past day), pw (past week), pm (past month), py (past year), or YYYY-MM-DDtoYYYY-MM-DD. | | `goggles` | string | No | Custom re-ranking rules via a Goggles URL or inline definition. | | `maximum_number_of_snippets` | integer | No | Maximum total snippets across all URLs (1–100). Defaults to 50. | | `maximum_number_of_snippets_per_url` | integer | No | Maximum snippets per URL (1–100). Defaults to 50. | | `maximum_number_of_tokens` | integer | No | Approximate maximum total tokens across all snippets (1024–32768). Defaults to 8192. | | `maximum_number_of_tokens_per_url` | integer | No | Maximum tokens per URL (512–8192). Defaults to 4096. | | `maximum_number_of_urls` | integer | No | Maximum number of URLs to include in the grounding response (1–50). Defaults to 20. | | `q` | string | Yes | The search query to retrieve grounding context for. Max 400 characters, 50 words. | | `safesearch` | string | No | Safe search filter level. | | `search_lang` | string | No | Language code for results (e.g., en, fr, de). Defaults to en. | ## `brave_local_descriptions` Fetch AI-generated descriptions for locations using IDs from a Brave web search response. Returns natural language summaries describing the place, its atmosphere, and what visitors can expect. | Name | Type | Required | Description | | --- | --- | --- | --- | | `ids` | `array` | Yes | Array of location IDs (up to 20) obtained from the locations field in a Brave web search response. | ## `brave_local_place_search` Search 200M+ Points of Interest (POIs) by geographic center and radius using Brave's Place Search API. Either 'location' (text name) OR both 'latitude' and 'longitude' (coordinates) must be provided. Supports an optional keyword query to filter results. Ideal for map applications and local discovery. | Name | Type | Required | Description | | --- | --- | --- | --- | | `count` | integer | No | Number of POI results to return (1–50). Defaults to 20. | | `country` | string | No | ISO 3166-1 alpha-2 country code (e.g., us, gb). Defaults to US. | | `latitude` | number | No | Latitude of the search center point (-90 to +90). Required together with longitude as an alternative to location name. | | `location` | string | No | Location name (e.g., 'san francisco ca united states'). Required unless latitude and longitude are both provided. | | `longitude` | number | No | Longitude of the search center point (-180 to +180). Required together with latitude as an alternative to location name. | | `q` | string | No | Optional keyword query to filter POIs (e.g., 'coffee shops', 'italian restaurants'). Omit for a general area snapshot. | | `radius` | number | No | Search radius in meters from the center point. | | `safesearch` | string | No | Safe search filter level. Defaults to strict. | | `search_lang` | string | No | Language code for results (e.g., en, fr). Defaults to en. | | `spellcheck` | boolean | No | Whether to enable spellcheck on the query. | | `units` | string | No | Measurement system for distances in the response. | ## `brave_local_pois` Fetch detailed Point of Interest (POI) data for up to 20 location IDs returned by a Brave web search response. Returns rich local business data including address, phone, hours, ratings, and reviews. Note: location IDs are ephemeral and expire after ~8 hours. | Name | Type | Required | Description | | --- | --- | --- | --- | | `ids` | `array` | Yes | Array of location IDs (up to 20) obtained from the locations field in a Brave web search response. | ## `brave_news_search` Search for news articles using Brave Search. Returns recent news results with titles, URLs, snippets, publication dates, and source information. Supports filtering by country, language, freshness, and custom re-ranking via Goggles. | Name | Type | Required | Description | | --- | --- | --- | --- | | `count` | integer | No | Number of news results to return (1–50). Defaults to 20. | | `country` | string | No | Country code for localised news (e.g., us, gb, de). | | `extra_snippets` | boolean | No | Include additional excerpt snippets per article. Defaults to false. | | `freshness` | string | No | Filter results by publish date: pd (past day), pw (past week), pm (past month), py (past year), or YYYY-MM-DDtoYYYY-MM-DD. | | `goggles` | string | No | Custom re-ranking rules via a Goggles URL or inline definition. | | `offset` | integer | No | Zero-based offset for pagination (0–9). Defaults to 0. | | `q` | string | Yes | The news search query string. | | `safesearch` | string | No | Safe search filter level. Defaults to strict. | | `search_lang` | string | No | Language code for results (e.g., en, fr, de). | | `spellcheck` | boolean | No | Whether to enable spellcheck on the query. Defaults to true. | | `ui_lang` | string | No | User interface language locale for response strings (e.g., en-US). | ## `brave_spellcheck` Check and correct spelling of a query using Brave Search's spellcheck engine. Returns suggested corrections for misspelled queries. | Name | Type | Required | Description | | --- | --- | --- | --- | | `country` | string | No | Country code for localised spellcheck (e.g., us, gb). | | `lang` | string | No | Language code for spellcheck (e.g., en, fr, de). | | `q` | string | Yes | The query string to spellcheck. | ## `brave_suggest_search` Get autocomplete search suggestions from Brave Search for a given query prefix. Useful for query completion, exploring related search terms, and building search UIs. | Name | Type | Required | Description | | --- | --- | --- | --- | | `count` | integer | No | Number of suggestions to return (1–20). Defaults to 5. | | `country` | string | No | Country code for localised suggestions (e.g., us, gb, de). | | `lang` | string | No | Language code for suggestions (e.g., en, fr, de). | | `q` | string | Yes | The partial query string to get suggestions for. | | `rich` | boolean | No | Whether to return rich suggestions with additional metadata. | ## `brave_summarizer_enrichments` Fetch enrichment data for a Brave AI summary key. Returns images, Q\&A pairs, entity details, and source references associated with the summary. | Name | Type | Required | Description | | --- | --- | --- | --- | | `key` | string | Yes | The opaque summarizer key returned in a Brave web search response when summary=true was set. | ## `brave_summarizer_entity_info` Fetch detailed entity metadata for entities mentioned in a Brave AI summary. Returns structured information about people, places, organizations, and concepts referenced in the summary. | Name | Type | Required | Description | | --- | --- | --- | --- | | `key` | string | Yes | The opaque summarizer key returned in a Brave web search response when summary=true was set. | ## `brave_summarizer_followups` Fetch suggested follow-up queries for a Brave AI summary key. Useful for building conversational search flows and helping users explore related topics. | Name | Type | Required | Description | | --- | --- | --- | --- | | `key` | string | Yes | The opaque summarizer key returned in a Brave web search response when summary=true was set. | ## `brave_summarizer_search` Retrieve a full AI-generated summary for a summarizer key obtained from a Brave web search response (requires summary=true on the web search). Returns the complete summary with title, content, enrichments, follow-up queries, and entity details. | Name | Type | Required | Description | | --- | --- | --- | --- | | `entity_info` | integer | No | Set to 1 to include detailed entity metadata in the response. | | `inline_references` | boolean | No | Add citation markers throughout the summary text pointing to sources. | | `key` | string | Yes | The opaque summarizer key returned in a Brave web search response when summary=true was set. | ## `brave_summarizer_summary` Fetch the complete AI-generated summary for a summarizer key. Returns the full summary content with optional inline citation markers and entity metadata. | Name | Type | Required | Description | | --- | --- | --- | --- | | `entity_info` | integer | No | Set to 1 to include detailed entity metadata in the response. | | `inline_references` | boolean | No | Add citation markers throughout the summary text pointing to sources. | | `key` | string | Yes | The opaque summarizer key returned in a Brave web search response when summary=true was set. | ## `brave_summarizer_title` Fetch only the title component of a Brave AI summary for a given summarizer key. | Name | Type | Required | Description | | --- | --- | --- | --- | | `key` | string | Yes | The opaque summarizer key returned in a Brave web search response when summary=true was set. | ## `brave_video_search` Search for videos using Brave Search. Returns video results with titles, URLs, thumbnails, durations, and publisher metadata. Supports filtering by country, language, freshness, and safe search. | Name | Type | Required | Description | | --- | --- | --- | --- | | `count` | integer | No | Number of video results to return (1–50). Defaults to 20. | | `country` | string | No | Country code for localised results (e.g., us, gb, de). | | `freshness` | string | No | Filter results by upload date: pd (past day), pw (past week), pm (past month), py (past year), or YYYY-MM-DDtoYYYY-MM-DD. | | `offset` | integer | No | Zero-based offset for pagination (0–9). Defaults to 0. | | `q` | string | Yes | The video search query string. | | `safesearch` | string | No | Safe search filter level. Defaults to moderate. | | `search_lang` | string | No | Language code for results (e.g., en, fr, de). | | `spellcheck` | boolean | No | Whether to enable spellcheck on the query. Defaults to true. | ## `brave_web_search` Search the web using Brave Search's privacy-focused search engine. Returns real-time web results including titles, URLs, snippets, news, videos, images, locations, and rich data. Supports filtering by country, language, safe search, freshness, and custom re-ranking via Goggles. | Name | Type | Required | Description | | --- | --- | --- | --- | | `count` | integer | No | Number of search results to return (1–20). Defaults to 20. | | `country` | string | No | Country code for search results (e.g., us, gb, de). Defaults to US. | | `extra_snippets` | boolean | No | Include up to 5 additional excerpt snippets per result. Defaults to false. | | `freshness` | string | No | Filter results by publish date. Use pd (past day), pw (past week), pm (past month), py (past year), or a date range YYYY-MM-DDtoYYYY-MM-DD. | | `goggles` | string | No | Custom re-ranking rules via a Goggles URL or inline definition to bias search results. | | `offset` | integer | No | Zero-based offset for pagination of results (0–9). Defaults to 0. | | `q` | string | Yes | Search query string. Max 400 characters, 50 words. | | `result_filter` | string | No | Comma-separated list of result types to include in the response. | | `safesearch` | string | No | Safe search filter level. Defaults to moderate. | | `search_lang` | string | No | Language code for result content (e.g., en, fr, de). Defaults to en. | | `spellcheck` | boolean | No | Whether to enable spellcheck on the query. Defaults to true. | | `summary` | boolean | No | Enable summarizer key generation in the response. Use the returned key with the Summarizer endpoints. | | `text_decorations` | boolean | No | Whether to include text decoration markers (bold tags) in result snippets. Defaults to true. | | `ui_lang` | string | No | User interface language locale for response strings (e.g., en-US, fr-FR). | | `units` | string | No | Measurement system for unit-bearing results. | --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |