brave

LLM context retrieval (RAG)

brave_llm_context

Read-only

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.

Input Schema

TableJSON Schema

Name	Required	Description
`count`	No	Maximum number of search results considered to select the LLM context data. Default 20, max 50.
`query`	Yes	The user's search query. Max 400 characters and 50 words.
`country`	No	2-letter country code (ISO 3166-1 alpha-2). Defaults to US.
`freshness`	No	Filter results by recency. Use pd, pw, pm, py, or YYYY-MM-DDtoYYYY-MM-DD.
`spellcheck`	No	Whether to spellcheck the query.
`search_lang`	No	2-letter language code for the search. Defaults to en.
`enable_local`	No	Whether to enable local recall.
`context_threshold_mode`	No	Mode used to determine the inclusion threshold for content.
`enable_source_metadata`	No	Enable source metadata enrichment (site_name, favicon) in the sources attribute.
`maximum_number_of_urls`	No	Maximum number of different URLs to include in LLM context.
`maximum_number_of_tokens`	No	Approximate maximum number of tokens to include in context. Default 8192, max 32768.
`maximum_number_of_snippets`	No	Maximum number of snippets (chunks of text) to include in LLM context. Default 50, max 256.
`maximum_number_of_tokens_per_url`	No	Maximum number of tokens to include per URL. Default 4096, max 8192.
`maximum_number_of_snippets_per_url`	No	Maximum number of snippets to include per URL. Default 50, max 100.

Schema Changelog

Changes observed during successful MCP inspections.

AddedMay 9, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true. Description adds that it returns text chunks, tables, code blocks, and a sources map, providing useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with core functionality, each sentence adds distinct value (purpose, differentiation, usage guidance). No waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given high schema coverage and read-only annotations, the description adequately covers tool behavior. Could mention response structure more, but sufficient for a RAG tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameter semantics are well-documented in schema. Description does not add extra parameter-specific meaning beyond schema, earning baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves pre-extracted, relevance-ranked web content using Brave's LLM Context API, optimized for AI agents and RAG, distinguishing it from traditional web search by returning actual content chunks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly contrasts with traditional web search, indicating when to use this tool over siblings like brave_web_search. Provides citation guidance but lacks explicit when-not usage instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All brave tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

LLM context retrieval (RAG)

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources