Brave Search

Live

API KEY

SEARCH

Every web search, news lookup, and citation your agent needs. Brave Search MCP gives your agent authenticated access to web search scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Brave Search account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Brave Search
agent · Acme Q3
Run
Find the latest news on enterprise SSO adoption trends from the past month.
S
brave_news_search
94ms
Research agent
6 relevant news articles. Top: Gartner Q4 report (SSO adoption +28% YoY), CIO Mag piece on SCIM mandates, TechCrunch on identity vendor consolidation.
Sources: 6 news articles, past month
bravesearchmcp
6 results
18:29
Message Claude...

Tools your research agent reaches for on Brave Search, scoped per user.

CALL ANY TOOL
Run web, news, image, and video searches with privacy-focused, freshness-controlled queries.
brave_web_search
Web search
Run a privacy-focused web search query with optional safe search and country filters.
Parameters
Name
Type
Required
Description
q
string
Required
Search query
count
integer
Optional
Number of results (max 20)
safesearch
string
Optional
off, moderate, or strict
country
string
Optional
Country code (e.g. US, IN)
brave_news_search
News search
brave_image_search
Image search
brave_video_search
Video search
Build your Agent
Drop the toolkit in, point it at the user, and your research agent can use Brave Search from the first run.
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["bravesearch"], toolNames: ["brave_web_search", "brave_news_search", "brave_image_search"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["bravesearch"], toolNames: ["brave_web_search", "brave_news_search", "brave_image_search"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["bravesearch"], toolNames: ["brave_web_search", "brave_news_search", "brave_image_search"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/bravesearch",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Brave Search.
Web & news
Copy the prompt
Copied
Search the web for [topic].
Copy the prompt
Copied
Find news on [topic] from the last week.
Copy the prompt
Copied
Get top 10 results on [query] from country [code].
Copy the prompt
Copied
Search images for [query].
Research & sourcing
Copy the prompt
Copied
Find recent articles about [competitor name].
Copy the prompt
Copied
Search for case studies on [industry].
Copy the prompt
Copied
Pull news mentions of [company] this month.
Copy the prompt
Copied
What are the top podcasts on [topic]?
Comparison & monitoring
Copy the prompt
Copied
Compare news sentiment on [topic A] vs [topic B].
Copy the prompt
Copied
List all sources covering [event].
Copy the prompt
Copied
Find video tutorials on [skill].
Copy the prompt
Copied
Surface trending topics in [niche].
SEE HOW AUTH WORKS
Users authorize Brave Search once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Brave Search
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Brave Search
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Brave Search
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Brave Search
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other research agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
SALES
Sales call prep agent
Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Search quota consumed by a shared key
A shared Brave Search API key looks fine in a demo. In production, every search request drains the same rate limit. Quota exhaustion from one tenant blocks all others. Scalekit stores the key per-tenant in the vault so each workspace gets isolated quota and clear attribution.
// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Brave Search today. Exa, Perplexity, Tavily tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
Frequently Asked Questions
Does the agent access Brave Search as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Brave Search api key stored?
Can I limit what the agent is allowed to do in Brave Search?
What happens when a user revokes Brave Search access?
How are Brave Search rate limits managed?
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""bravesearch"": {
""url"": ""https://mcp.scalekit.com/bravesearch"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.bravesearch]
url = ""https://mcp.scalekit.com/bravesearch""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""bravesearch"": {
""url"": ""https://mcp.scalekit.com/bravesearch"",
""type"": ""http""
}
}
}