Connect
Optimize
Secure
Live 13 Actions
Brave Search MCP Server
for AI Agents
Connect your AI agent to StackOne's Brave Search MCP server and give it ready-to-use MCP tools out of the box. Auth, tool execution, and security all managed.
Brave Search MCP Server
Built by 
StackOne
StackOne 
Coverage
13 Agent Actions
Create, read, update, and delete across Brave Search — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Brave Search MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Brave Search tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Brave Search call.
Tools Discovery →What is the Brave Search MCP Server?
A Brave Search MCP server lets AI agents read and write Brave Search data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Brave Search MCP server ships with pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Brave Search MCP Tools
Every action from Brave Search's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Web Searchs
- Web Search
Search the web using Brave Search
Web Rich Results
- Get Web Rich Results
Fetch real-time rich data (weather, stocks, sports) using a callback_key from a prior web_search call with enableRichCallback set to true
LLM Contexts
- Create LLM Context
Retrieve token-bounded web search snippets for LLM ingestion via POST body (use instead of llm_context_get when query params would exceed URL length limits)
- Get LLM Context
Retrieve pre-extracted, token-bounded web search snippets optimised for direct LLM ingestion rather than ranked links
Chat Completions
- Create Chat Completion
Generate an AI answer using Brave Search context
News
- Search News
Search for news articles using Brave Search
Images
- Search Images
Search for images using Brave Search
Videos
- Search Videos
Search for videos using Brave Search
Places
- Search Places
Search for local places and businesses
Local POIs
- Get Local POIs
Retrieve enriched POI details (photos, hours, ratings) by IDs obtained from place_search or web_search results
Local Descriptions
- Get Local Descriptions
Retrieve AI-generated text descriptions for locations by POI IDs obtained from place_search or web_search results
Suggestions
- Get Search Suggestions
Get autocomplete suggestions for a search query
Check Spellings
- Check Spelling
Spell-check a search query
Set Up Your Brave Search MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Brave Search in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
Brave Search MCP Server FAQ
Does StackOne have a Brave Search MCP server?
Yes. StackOne offers a hosted Brave Search MCP server, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Brave Search MCP server vs direct API integration — what's the difference?
A Brave Search MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Brave Search. A Brave Search MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Brave Search at runtime. StackOne provides both.
How does Brave Search authentication work for AI agents?
Brave Search authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Brave Search account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Brave Search MCP tools vulnerable to prompt injection?
Yes — Brave Search MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Brave Search agent and how do I avoid it?
Context bloat happens when Brave Search tool schemas and API responses eat your Brave Search agent's memory, preventing it from reasoning effectively. A single Brave Search query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Brave Search agent can access?
Yes — you can limit which actions your Brave Search agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Brave Search MCP server?
Yes — you can create custom agent actions for your Brave Search MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Brave Search's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Brave Search MCP server?
Skip a Brave Search MCP server if your integration is purely software-to-software — direct Brave Search API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Brave Search actions at runtime.
What AI frameworks and AI clients does the StackOne Brave Search MCP server support?
The StackOne Brave Search MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.