Skills/npm/mcp-server

mcp-server@2.6.10

VERIFIED· not started

Publisher claims: "BrowserStack's Official MCP Server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher browserstack · publishing for 575 daysInstalls 124KLast detonated 28 min ago
$claude mcp add mcp-server -- npx -y @browserstack/mcp-server
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ASK_BROWSERSTACK_AUTH_TOKEN_URLBROWSERSTACK_ACCESS_KEYConfiguration, not credentials: ASK_BROWSERSTACK_ATLAS_URL, ASK_BROWSERSTACK_RELAY_TRANSPORT, BROWSERSTACK_AUTOMATION_BASE_URL, BROWSERSTACK_O11Y_UI_BASE_URL, BROWSERSTACK_USERNAME, DEV_MODE, MCP_UPLOAD_BASE_DIR, O11Y_TFA_RCA_BASE_URL, REMOTE_MCP, USE_OWN_LOCAL_BINARY_PROCESS
Where it talks to
browserstack.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for ASK_BROWSERSTACK_AUTH_TOKEN_URL, BROWSERSTACK_ACCESS_KEY and talks to browserstack.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets ASK_BROWSERSTACK_AUTH_TOKEN_URL=browserstack.com,BROWSERSTACK_ACCESS_KEY=browserstack.com -- npx -y @browserstack/mcp-server

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

What changed since 2.6.9

vet-skills diff mcp-server 2.6.9 2.6.10

In the sandbox, this version reached for nothing 2.6.9 did not. Compared from the two recorded runs, not from source.

No longer contacted
percy.io

2.6.9 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

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; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 13 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
13sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-g0C6j8/task/home/.npm/_logs/2026-11-18T16_23_43_271Z-debug-0.log
13sclaimednot started: dependency install failed (exit 1); the server itself was not observed
13sprocessscript backend runs setup only
13sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commanddist/lib/local.js:42 · Process kill command — agent can terminate processes// Check and kill any existing BrowserStackLocal processes before starting new oneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/config.js:58 · Process kill command — agent can terminate processes// ASK_BROWSERSTACK_DISABLED is deliberately NOT here: it is a kill switch, and readingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈47 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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.