AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
ToolsCategoriesTrendingNewCompare
Home/
RAG / Knowledge Base/
Brave Search MCP
Brave Search MCP logo

Brave Search MCP

Active·★ 88.6k·MIT·Updated 2026-07-10
★ Most Popular★ Trending★ Essential

The Brave Search MCP server is part of the official Model Context Protocol reference implementations. It gives AI agents real-time web search via the Brave Search API, enabling access to current news, facts, and web content that the model's training data doesn't cover. A foundational MCP integration for any agent requiring up-to-date information retrieval.

Brave Search MCP is currently grouped under RAG / Knowledge Base, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Real-time web search via Brave Search API with configurable result count and freshness and Giving AI agents access to current events, news, and web data beyond training cutoff. The listed license is MIT, which is useful when adoption constraints matter. It also shows measurable community traction with 88.6k GitHub stars.

#Model Context Protocol#LLM#AI Agents#Reference Servers#SDKs#Web Browsing
$ Install
$ npx -y @modelcontextprotocol/server-memory
↗ Visit site★ GitHub
01

Features

01Real-time web search via Brave Search API with configurable result count and freshness
02Part of the official MCP reference server collection maintained by the MCP steering group
03Supports web search, news search, and local POI search
04Configurable filtering by country, language, and time range
05Free tier available; paid tier for higher rate limits
02

Why choose it

+Real-time web search via Brave Search API with configurable result count and freshness
+Giving AI agents access to current events, news, and web data beyond training cutoff
+Ships with a public repository and a MIT license, which makes adoption and review easier.
+The latest recorded update is 2026-07-10, which suggests the project is still actively maintained.
03

Trade-offs

!Compatibility coverage looks narrow, so it is worth validating your target runtime before committing to it.
!There are at least 8 related tools in the same category, so the best choice is easier to make after side-by-side comparison.
04

Compatibility

Claude Desktop
Native
Verified via docs
Cursor
Supported
Verified via docs
05

Quick start

1
$ npx -y @modelcontextprotocol/server-memory
06

Use cases

↳Giving AI agents access to current events, news, and web data beyond training cutoff
↳Building research agents that verify facts with live search results
↳Augmenting any MCP-compatible AI assistant with real-time web search
07

How it compares

≈Brave Search MCP sits in the RAG / Knowledge Base category, so it makes more sense to evaluate it alongside tools like mindsdb instead of in isolation.
≈If your main need is closer to "Giving AI agents access to current events, news, and web data beyond training cutoff", that use case is a better lens for comparison than broad feature checklists alone.
≈Brave Search MCP uses a MIT license, and community traction are both easier to judge in category context.
08

Alternatives

mindsdb logo
mindsdb★ 39.4k
Federated Query Engine for AI - The only MCP Server you'll ever need
vs →
TrendRadar logo
TrendRadar★ 60.6k
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
vs →
worldmonitor logo
worldmonitor★ 61.9k
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
vs →
headroom logo
headroom★ 59.5k
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
vs →
ragflow logo
ragflow★ 85.2k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
vs →
Context7 logo
Context7★ 59.2k
MCP Server that provides up-to-date code documentation for LLMs and AI code editors.
vs →
GitHub MCP Server logo
GitHub MCP Server★ 31.5k
GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).
vs →
MaxKB logo
MaxKB★ 22.1k
An open-source platform for building enterprise-grade agents. Powerful and easy to use.
vs →
See all alternatives →

Related searches

Brave Search MCP AlternativesBest RAG / Knowledge Base Tools 2026Open Source RAG / Knowledge BaseBrave Search MCP TutorialBrave Search MCP Vs CompetitorsModel Context ProtocolLLMAI Agents

Comments

Log in to leave a comment
  • ?
    usr_seed_0827May 25, 2026

    rate limits on the free tier are fine for personal use. hit them quickly at team scale — factor that into planning

  • ?
    usr_seed_0452May 6, 2026

    The independence from Google means no bot detection or rate limit surprises

  • ?
    usr_seed_0936May 2, 2026

    works great for building research agents. pairs well with a document storage MCP server for a complete research workflow

  • ?
    usr_seed_0933Apr 6, 2026

    My assistant was giving stale answers until I added this. Night and day difference for anything time-sensitive.

  • ?
    usr_seed_0079Mar 29, 2026

    set this up alongside Claude in under 10 mins. the real-time search completely changes what the agent can answer

  • ?
    usr_seed_0355Mar 25, 2026

    Runs reliably in production. Response times are consistent around 300-500ms. Works cleanly alongside other MCP servers in a multi-server setup.

  • ?
    usr_seed_0311Mar 25, 2026

    Covered this in my MCP tooling roundup — for any agent that needs current information, this is the obvious first integration to add.

  • ?
    usr_seed_0760Mar 23, 2026

    Real-time internet search without tracking in AI workflows is the right default

  • ?
    usr_seed_0488Mar 15, 2026

    Brave index coverage is solid for technical queries, rarely misses relevant results

  • ?
    usr_seed_0755Mar 14, 2026

    Much more reliable than scraping Google for production AI search workflows

  • ?
    usr_seed_0855Feb 27, 2026

    Brave Search MCP is our go-to for giving agents real-time web access. The API is clean and the results are less SEO-spammy than alternatives.

  • ?
    usr_seed_0664Feb 14, 2026

    Swapped out a different search API for Brave Search MCP. Better freshness on news queries and the rate limits are more generous on the paid tier.

  • ?
    usr_seed_0931Jan 7, 2026

    The filtering options (country, freshness, result count) give useful control over retrieval quality.

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07How it compares08Alternatives
Stats
GitHub Stars★ 88.6k
Last commit1w ago
StatusActive
LicenseMIT
CategoryRAG / Knowledge Base
Trend (30d)
+3.5k↑ 4.9%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.