Skills/npm/brewpage-mcp

brewpage-mcp@3.2.1

VERIFIED

Publisher claims: "MCP server for BrewPage — publish and manage HTML, sites, KV, JSON and files from AI assistants, including pages that save visitor answers (forms, polls) with Page data" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher kochetkov-ma · publishing for 236 daysInstalls 10,748Last detonated 34 min ago
$claude mcp add brewpage-mcp -- npx -y brewpage-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
ACCOUNT_TOKENS_PAGEBREWPAGE_MCP_BRIDGE_SERVICE_SECRETBREWPAGE_MCP_CREDENTIAL_FILEDOMAIN_TOKENS_PAGEOWNER_TOKEN_ENVConfiguration, not credentials: BREWPAGE_ACCOUNT_ORIGIN, BREWPAGE_BACKEND_URL, BREWPAGE_MCP_CATALOG, BREWPAGE_MCP_HOST, BREWPAGE_MCP_ISSUER, BREWPAGE_MCP_PORT, BREWPAGE_MCP_RESOURCE_URL, BREWPAGE_MCP_STATE_DIR, BREWPAGE_MCP_TOOL_SELECTION, BREWPAGE_PUBLIC_ORIGIN, BREWPAGE_URL
Where it talks to
brewpage.app (its own)Also example.org — 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 real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names example.org as well as its own vendor. The guard injects ACCOUNT_TOKENS_PAGE, BREWPAGE_MCP_BRIDGE_SERVICE_SECRET, BREWPAGE_MCP_CREDENTIAL_FILE, DOMAIN_TOKENS_PAGE, OWNER_TOKEN_ENV only into requests to brewpage.app (and its subdomains) and refuses the rest.

$vet-skills run --secrets ACCOUNT_TOKENS_PAGE=brewpage.app,BREWPAGE_MCP_BRIDGE_SERVICE_SECRET=brewpage.app,BREWPAGE_MCP_CREDENTIAL_FILE=brewpage.app,DOMAIN_TOKENS_PAGE=brewpage.app,OWNER_TOKEN_ENV=brewpage.app -- npx -y brewpage-mcp

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 2026-11-22 and scored it 88/100 (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 · 26 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.3sprocessdependency install exit 0
25sfilesystemread ~/.config/brewpage-mcp/5d29a4919bd476d40b23c250d3f93109fccec9fa9954ce3345e9dcd406cc9d2e.json outside project
25sclaimed13 tools: publish, list_publications, read_publication, update_publication, publication_settings, delete_publication, read_page_data, write_page_data, delete_page_data, domains, account, notifications, get_guide
25stoolsf7a62ff9bcc36c1e
25stoolsd486ab0805cb93d5
25stools7d23c9f14b854bed
25stools919889f85ca3b73f
25stools3a9379182727318b
25stools90da0bb87e5149fd
25stools9c78d738176ae030
25stools39ddde5157e40488
25stoolsff75589b239c1462
25stoolsfc5992bd666eef9a
25stools766b46e418d75186
25stools4908a6873420c37d
25stools14e356d11384cc2b
25sprocessscript backend runs setup only
25sprocessno install scripts to re-run

Static findings

HIGH
Tool description instructs the agent: credential exfiltration instructionmcp:tools/publish:2 · Instruction aimed at the agent: credential exfiltration instructionor key; encrypted by this server before upload","type":"string"},"ttl":{"description":"kind=secret only. How long it stays readable, default 7d","type":"strinFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST01

No other findings across 8,233 lines in 52 files.

Cost to the agent

Instructions loaded
≈78 tok
1 file · 52 in bundle
Tool list per prompt
≈4,934 tok
13 tools · 380 per tool
Handshake
985 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 252

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 brewpage-mcp@3.2.1 as of 9 min ago. This is the package itself, not its dependencies.

brewpage-mcp@3.2.1 safety verdict: Verified — KillerSkills