Skills/npm/mcp-server

mcp-server@0.65.17

VERIFIED

Publisher claims: "Official Porkbun MCP server, built and maintained by Porkbun — exposes the Porkbun v3 API as tools for AI agents (ChatGPT, Claude, Cursor, etc.)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher porkbunllc · publishing for 195 daysInstalls 11,744Last detonated 5 h ago
$claude mcp add mcp-server -- npx -y @porkbunllc/mcp-server
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
OAUTH_ISSUERPORKBUN_API_KEYPORKBUN_SECRET_API_KEYPORKBUN_X402_PRIVATE_KEYConfiguration, not credentials: MCP_PUBLIC_URL, OPENAI_APPS_CHALLENGE, PORKBUN_BASE_URL, PORKBUN_DOCS_BASE, PORKBUN_X402_MAX_CENTS
Where it talks to
porkbun.com (its own)
What the honeypot saw
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. It asks for OAUTH_ISSUER, PORKBUN_API_KEY, PORKBUN_SECRET_API_KEY, PORKBUN_X402_PRIVATE_KEY and talks to porkbun.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.

$vet-skills run --secrets OAUTH_ISSUER=porkbun.com,PORKBUN_API_KEY=porkbun.com,PORKBUN_SECRET_API_KEY=porkbun.com,PORKBUN_X402_PRIVATE_KEY=porkbun.com -- npx -y @porkbunllc/mcp-server

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

What changed since 0.65.4

vet-skills diff mcp-server 0.65.4 0.65.17

This version reaches for something 0.65.4 did not: 4 new tools (build_agent_manifest, publish_agent_manifest, verify_agent_manifest, verify_artifact) · 3 rewritten tool descriptors (delete_hosting, deploy_site, update_hosting_auto_renew). Compared from the two recorded runs, not from source.

New tools
build_agent_manifest, publish_agent_manifest, verify_agent_manifest, verify_artifact
Rewritten tool descriptors
delete_hosting, deploy_site, update_hosting_auto_renew
Tools removed
delete_wordpress_staging, set_wordpress_staging_environment, set_wordpress_staging_outbound, set_wordpress_staging_password

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 2026-11-19 and scored it 84/100 (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 · 43 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
22sprocessdependency install exit 0
42sclaimed169 tools: ping, check_domain, check_domains, get_registration_requirements, get_pricing, list_marketplace, list_domains, get_domain, get_balance, get_auto_topup, top_up_with_usdc, top_up_with_card_mpp, send_phone_verification_code, confirm_phone_verification, send_email_verification_code, confirm_email_verification, get_usdc_topup_status, list_invoices, get_invoice, get_invoice_pdf, configure_auto_topup, top_up_account_credit, get_api_settings, get_nameservers, list_dns_records
42stools41ffeb68a8053dc5
42stools3a9299de23cf513f
42stools772277171e67c1ba
42stools30d3be0f814370ea
42stoolsbf5cadef9bfa3f19
42stools22f64469b3d32af6
42stoolsfc62d46cb02ebf5b
42stools39fc0dc4bac8b160
42stoolsd90513d845862953
42stoolsfbd7b9d686556dc3
42stools3c58a5202727725c
42stoolse7754fee09adee7b
42stools16e58b4ef69ac6cf
42stools3ec071e4084a0ee4
42stoolse7e473db1c9f7f52
42stools5a4d5c2d55fa83a0
42stools762542810bcfc7bd
42stools14609a74c4f6d632
42stoolse18a00d3cedc7a6a
42stools7c833e4a6c0c0e73
42stools1bfcd4a2d79df20d
42stools5a479120233137c3
42stools9c940bf01a6cf64d
42stools35a2e88e69057f4f
42stools8f2136aac9e037b0
42stools5b215e3b941021f2
42stools71b98bb7784fb436
42stools65f773da1b6fffcb
42stoolsa4bce3abc44f8e15
42stools16bc32f25b863697
42stools008ceb218f673dd9
42stoolsf9ddad81fd9e6681
42stoolscba00baa3e00a963
42stools5f0b149924d710c3
42stoolsb6a4ac3bdfadb53d
42stoolsba9a256b70b08d76
42stools1b210f44559d99f9
42stoolsd46d075fa6f14a14
42stoolsfe871eb5057fa9e2
42stools41d9925dfa81bb67
42stools4f92229487c22c4a
42stools90f3f5a73acdf29d
42stools5083e0e9d5f2b8a0
42stoolsa53a24d06311dcb6
42stoolscda037b10944ce9a
42stoolsc3436cd7a4dbbde5
42stoolse867b5b32ebc13bb
42stoolsd250641e119200c2
42stools020d5cd9575e8056
42stoolsea6fab994b834efc
42stools0f5c8a264290c6ee
42stools18bb66a5555230ec
42stools2437f12847188687
42stools0a0f2cd2a881b690
42stoolsf91bb0818e251ce5
42stoolsf2f498774b731046
42stools942aa224fcdeac37
42stoolscdb62bb07fe0ed9c
42stoolsb3276bc838e9054d
42stools35799db9295c64f7
42stools38145ab0b7bc0352
42stools310827e162028ed2
42stoolsc9860a44e673331c
42stools1d164a0594211ba7
42stools406fcf16ab828cec
42stools6c1c67df2151c5ae
42stools29a90d537a26c4ac
42stools60c5a85eb42ad117
42stools71046bcdb1bacf49
42stools44289c3c18c5ff28
42stoolscdabb3915308799e
42stools0acc5be11496502f
42stoolsef73963cdc59c7ca
42stools332dc911f1ddfece
42stools24c5e0c341afc843
42stoolsa6c4bd19f4b8215e
42stools8fa279c3930e4942
42stoolsc90a381c8adfd766
42stools1b9d846cfc345e94
42stools6e8c5653fa9427dc
42sprocessscript backend runs setup only
42sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/tools.js:1922 · File type combined with upload action — agent may exfiltrate local data files…tatic Hosting. TEXT FILES GO IN `text`, AS WRITTEN: for .html, .css, .js, .svg, .json, .txt and .xml send { path, text } with the file's contents exactly as you wrote them. Do NOT base64-encode text files; base64 is slow and error-prone fo…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/tools.js:89 · npx invocation of non-well-known package — may execute untrusted code… No shell? Link's own MCP server does the same where your client can run one (\`npx -y @stripe/link-cli --mcp\`, or \`link-cli mcp add\` to register it); without eith…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Tool description instructs the agent: "do not tell the user"mcp:tools/buy_closeout:1 · Instruction aimed at the agent: "do not tell the user"releases it over the following days, so do not tell the user it is in their account: poll list_domains or watch the domaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈75 tok
1 file · 11 in bundle
Tool list per prompt
≈59,923 tok
169 tools · 355 per tool
Handshake
7209 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 791

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 @porkbunllc/mcp-server@0.65.17 as of 4 h ago. This is the package itself, not its dependencies.