Brave Search
brave_llm_context
Retrieves pre-extracted, relevance-ranked web content using Brave's LLM Context API, optimized for AI agents, LLM grounding, and RAG pipelines. Unlike a traditional web search that returns links and short descriptions, this tool returns the actual substance of matching pages — text chunks, tables, code blocks, and structured data — so the model can reason over it directly. When relaying results in markdown-supporting environments, cite source URLs from the `sources` map.
Remote brave
Other tools also called brave_llm_context?
See providers with this name
Input Schema
{
"type": "object",
"properties": {
"count": {
"type": "integer",
"default": 20,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of search results considered to select the LLM context data. Default 20, max 50."
},
"query": {
"type": "string",
"maxLength": 400,
"description": "The user's search query. Max 400 characters and 50 words."
},
"country": {
"type": "string",
"default": "US",
"maxLength": 2,
"minLength": 2,
"description": "2-letter country code (ISO 3166-1 alpha-2). Defaults to US."
},
"freshness": {
"type": "string",
"description": "Filter results by recency. Use pd, pw, pm, py, or YYYY-MM-DDtoYYYY-MM-DD."
},
"spellcheck": {
"type": "boolean",
"default": true,
"description": "Whether to spellcheck the query."
},
"search_lang": {
"type": "string",
"default": "en",
"description": "2-letter language code for the search. Defaults to en."
},
"enable_local": {
"type": "boolean",
"description": "Whether to enable local recall."
},
"context_threshold_mode": {
"enum": [
"disabled",
"strict",
"lenient",
"balanced"
],
"type": "string",
"default": "balanced",
"description": "Mode used to determine the inclusion threshold for content."
},
"enable_source_metadata": {
"type": "boolean",
"description": "Enable source metadata enrichment (site_name, favicon) in the sources attribute."
},
"maximum_number_of_urls": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Maximum number of different URLs to include in LLM context."
},
"maximum_number_of_tokens": {
"type": "integer",
"default": 8192,
"maximum": 32768,
"minimum": 1024,
"description": "Approximate maximum number of tokens to include in context. Default 8192, max 32768."
},
"maximum_number_of_snippets": {
"type": "integer",
"default": 50,
"maximum": 256,
"minimum": 1,
"description": "Maximum number of snippets (chunks of text) to include in LLM context. Default 50, max 256."
},
"maximum_number_of_tokens_per_url": {
"type": "integer",
"default": 4096,
"maximum": 8192,
"minimum": 512,
"description": "Maximum number of tokens to include per URL. Default 4096, max 8192."
},
"maximum_number_of_snippets_per_url": {
"type": "integer",
"default": 50,
"maximum": 100,
"minimum": 1,
"description": "Maximum number of snippets to include per URL. Default 50, max 100."
}
}
}