Skills/npm/brave-search-mcp-server

brave-search-mcp-server@2.1.5

VERIFIED

Publisher claims: "Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher brave · publishing for 489 daysInstalls 180KLast detonated 17 min ago
$claude mcp add brave-search-mcp-server -- npx -y @brave/brave-search-mcp-server
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
API_KEYBRAVE_API_KEYBRAVE_API_KEY_FILE or --brave-api-key / --brave-api-key-fileConfiguration, not credentials: BRAVE_MCP_ALLOWED_HOSTS, BRAVE_MCP_ALLOWED_ORIGINS, BRAVE_MCP_DISABLED_TOOLS, BRAVE_MCP_ENABLED_TOOLS, BRAVE_MCP_HOST, BRAVE_MCP_LOG_LEVEL, BRAVE_MCP_PORT, BRAVE_MCP_STATELESS, BRAVE_MCP_TEST_IMAGE, BRAVE_MCP_TRANSPORT
Where it talks to
brave.com (its own)Also slack.com, a.example, b.example, c.example, allowed.example, evil.example, amazon.com, reuters.com, nytimes.com, bbc.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
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 slack.com, a.example, b.example, c.example, allowed.example, evil.example, amazon.com, reuters.com, nytimes.com, bbc.com as well as its own vendor. The guard injects API_KEY, BRAVE_API_KEY, BRAVE_API_KEY_FILE only into requests to brave.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets API_KEY=brave.com,BRAVE_API_KEY=brave.com,BRAVE_API_KEY_FILE=brave.com -- npx -y @brave/brave-search-mcp-server

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

What changed since 2.1.4

vet-skills diff brave-search-mcp-server 2.1.4 2.1.5

This version reaches for something 2.1.4 did not: 1 new host (amazon.com) · 1 new credential variable (API_KEY) · 4 rewritten tool descriptors (brave_llm_context, brave_local_search, brave_place_search, brave_web_search). Compared from the two recorded runs, not from source.

New hosts
amazon.com
New credential variables
API_KEY
Rewritten tool descriptors
brave_llm_context, brave_local_search, brave_place_search, brave_web_search

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-17 and scored it 90/100 (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 · 54 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
14sprocessdependency install exit 0
34sprocessrelaunched with a decoy BRAVE_API_KEY (tagged; nothing real)
54sclaimed8 tools with a decoy BRAVE_API_KEY: brave_web_search, brave_local_search, brave_video_search, brave_image_search, brave_news_search, brave_summarizer, brave_llm_context, brave_place_search
54stools37c96904a2bd6cdf
54stoolsc58bbf4bfc0ef8ab
54stools70cd77f52a959c9d
54stoolsb603b19d20d0342c
54stools6138e22a4f20a920
54stools49e5aff563aba568
54stools5a904701f573c4e6
54stools824a9ba00b7126e1
54sprocessscript backend runs setup only
54sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandpackage.json:29 · File permission modification command — agent changes file ownership/permissions"build": "shx rm -rf dist && tsc && shx chmod +x dist/*.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsdist/docker.e2e.js:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈66 tok
1 file · 60 in bundle
Tool list per prompt
≈8,321 tok
8 tools · 1040 per tool
Handshake
3385 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 832

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

Not checked against OSV yet; the weekly check has not reached this version.