Skills/npm/mcp-server

mcp-server@0.1.21

VERIFIED

Publisher claims: "Model Context Protocol server for Zyphr — wraps the Zyphr API as MCP tools for AI clients" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher zyphr-dev · publishing for 158 daysInstalls 1,110Last detonated 1 h ago
$claude mcp add mcp-server -- npx -y @zyphr-dev/mcp-server
WatchReport an issue

Coverage

Started with a decoy ZYPHR_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in ZYPHR_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
ZYPHR_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
ZYPHR_API_KEYZYPHR_APPLICATION_SECRETZYPHR_WEBHOOK_SECRETConfiguration, not credentials: ZYPHR_ALLOWED_TOOLS, ZYPHR_APPLICATION_KEY, ZYPHR_BASE_URL, ZYPHR_READ_ONLY
Where it talks to
zyphr.dev (its own)Also nuget.org, rubygems.org, go.dev, packagist.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 a real credential

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names nuget.org, rubygems.org, go.dev, packagist.org as well as its own vendor. The guard injects ZYPHR_API_KEY, ZYPHR_APPLICATION_SECRET, ZYPHR_WEBHOOK_SECRET only into requests to zyphr.dev (and its subdomains) and refuses the rest.

$vet-skills run --secrets ZYPHR_API_KEY=zyphr.dev,ZYPHR_APPLICATION_SECRET=zyphr.dev,ZYPHR_WEBHOOK_SECRET=zyphr.dev -- npx -y @zyphr-dev/mcp-server

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

What changed since 0.1.16

vet-skills diff mcp-server 0.1.16 0.1.21

This version reaches for something 0.1.16 did not: 14 new tools (create_inbox_draft, create_inbox_label, forward_inbound_email, get_inbox_thread, …) · 1 rewritten tool descriptor (list_inbound_emails). Compared from the two recorded runs, not from source.

New tools
create_inbox_draft, create_inbox_label, forward_inbound_email, get_inbox_thread, list_inbox_drafts, list_inbox_labels, list_inbox_thread_emails, list_inbox_threads, list_inboxes, reply_to_inbox_thread, send_inbox_draft, set_inbox_thread_labels +2
Rewritten tool descriptors
list_inbound_emails

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 2026-11-22 and scored it 85/100 (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 · 52 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
12sprocessdependency install exit 0
32sprocessrelaunched with a decoy ZYPHR_API_KEY (tagged; nothing real)
52sclaimed48 tools with a decoy ZYPHR_API_KEY: send_email, send_push, send_sms, send_inbox_message, list_templates, get_template, render_template, create_template, find_subscriber, list_subscribers, create_subscriber, update_subscriber, set_subscriber_preferences, list_webhooks, create_webhook, get_webhook_deliveries, add_domain, list_domains, get_domain, verify_domain, list_inbound_emails, get_inbound_email, get_inbound_attachment_url, list_inboxes, list_inbox_threads
52stools367bac5767d00949
52stools706f586fabbff2fc
52stools996b889c8fd8a5f8
52stools7b9dc4e68b8e97a3
52stoolsa29640b8f0522a0b
52stoolse71876eda0dc4c76
52stoolsdb78c2da0362f6be
52stools26e02a49eeea3b52
52stools28071041493bc81e
52stools2021503bff03c1c4
52stools9fa3b073958279b9
52stools45601bbaa1bc81d8
52stoolsd9abca4a4edf7283
52stools6dd05e09e2f9d972
52stools76122eac4cb20a5f
52stoolsf97ece0352edb28f
52stools3c287744a49b4964
52stoolsfeb9e9688b5897c1
52stoolsef96bbfc48fe0275
52stools9532e95c840bbce1
52stools20598b3a070e2ef2
52stoolse27b00a370e60ef6
52stoolsb9ca8b8f20eb6942
52stools44b916a5b716073c
52stoolsb8882cba804106c3
52stoolse189e22a6f80f220
52stoolsce690418944bcc89
52stoolsbf3c235a0eb3e9b2
52stools50bc5cae560ec514
52stools31ac686cb28a018d
52stools8f280bbf94e367e0
52stools1c4b8e2d37195b8c
52stools477a3201d588c6f8
52stoolse6b04ded8bb6a90b
52stoolsc085cbc4c41d127e
52stools82786a8abab080f5
52stools60c154353ed4a4d4
52stools8d3b3ff34f338dbf
52stools27c353e5abe9c2b2
52stools0241b9723c2f4933
52stools613c101d1c00a74f
52stools1e28a7f39d111e55
52stoolsf1754d0553723711
52stools7398f135d782c7b9
52stools1f7e3178304ae563
52stools848411e5fdbf0c74
52stoolsd5587d584c8c2d46
52stools532b43d8f7090325
52sprocessscript backend runs setup only
52sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/index.js:2271 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Add ZYPHR_WEBHOOK_SECRET to your .env file \u2014 get it from `zyphr.webhooks.rotateWebhookSecret(id)` or the Zyphr dashboard.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/index.js:1795 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Add ZYPHR_API_KEY to your .env file.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/index.js:1959 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Add ZYPHR_API_KEY to your .env file.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/index.js:1386 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Add ZYPHR_API_KEY to your .env file (run get_sdk_install_for_language to confirm the install).",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/index.js:1458 · File type combined with upload action — agent may exfiltrate local data files…n\nexport async function POST(req: Request) {\n const { to, name } = (await req.json()) as { to: string; name: string };\n const result = await zyphr.emails.sendEmail({\n to: [{ email: to, name }],\n subject: `Welcome, ${name}!`,\n …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsdist/index.js:2122 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Add ZYPHR_API_KEY to your .env file.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/index.js:2311 · File type combined with upload action — agent may exfiltrate local data files…const event = JSON.parse(payload) as { type: string; data: unknown };\n console.log('zyphr event', event.type);\n res.sendStatus(204);\n});\n", overwrite: false } ], …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈60 tok
1 file · 5 in bundle
Tool list per prompt
≈7,848 tok
48 tools · 164 per tool
Handshake
949 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 139

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 @zyphr-dev/mcp-server@0.1.21 as of 31 min ago. This is the package itself, not its dependencies.