Skills/npm/mcp-brave-search

mcp-brave-search@1.0.1

VERIFIED

Publisher claims: "Brave Search MCP Server - Web and News Search via stdio" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher yuandeshoulian · publishing for 368 daysInstalls 17,884Last detonated 1 h ago
$claude mcp add mcp-brave-search -- npx -y mcp-brave-search
WatchReport an issue

Coverage

Started with a decoy BRAVE_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in BRAVE_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
BRAVE_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
BRAVE_API_KEYConfiguration, not credentials: BRAVE_API_BASE_URL
Where it talks to
no vendor host named in the codeAlso brave.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names brave.com as well as its own vendor. The guard injects BRAVE_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y mcp-brave-search

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-20 and scored it 95/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 47 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.1sprocessdependency install exit 0
27sprocessrelaunched with a decoy BRAVE_API_KEY (tagged; nothing real)
47sclaimed2 tools with a decoy BRAVE_API_KEY: brave_web_search, brave_news_search
47stools0a107e0af87f3d40
47stools93feca8c75db37da
47sprocessscript backend runs setup only
47sprocessno install scripts to re-run

Static findings

No findings across 1,334 lines in 20 files.

Cost to the agent

Instructions loaded
≈52 tok
1 file · 20 in bundle
Tool list per prompt
≈659 tok
2 tools · 330 per tool
Handshake
630 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 189

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for mcp-brave-search@1.0.1 as of 40 min ago. This is the package itself, not its dependencies.