Skills/npm/kudosity-mcp

kudosity-mcp@0.5.0

VERIFIED

Publisher claims: "Send SMS, MMS and WhatsApp, manage contacts and webhooks, from AI agents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher kudosity · publishing for 110 daysInstalls 0Last detonated 4d ago
$claude mcp add kudosity-mcp -- npx -y kudosity-mcp
WatchReport an issue

Coverage

Started with a decoy KUDOSITY_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in KUDOSITY_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
KUDOSITY_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
KUDOSITY_API_KEYKUDOSITY_API_SECRETConfiguration, not credentials: KUDOSITY_API_BASE_URL, KUDOSITY_SPEC_V1_URL, KUDOSITY_SPEC_V2_URL, KUDOSITY_V1_BASE_URL, LIST_PATHS
Where it talks to
kudosity.com (its own)Also transmitmessage.com, transmitsms.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 transmitmessage.com, transmitsms.com as well as its own vendor. The guard injects KUDOSITY_API_KEY, KUDOSITY_API_SECRET only into requests to kudosity.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets KUDOSITY_API_KEY=kudosity.com,KUDOSITY_API_SECRET=kudosity.com -- npx -y kudosity-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 2026-11-10 and scored it 93/100 (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 · 45 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.7sprocessdependency install exit 0
25sprocessrelaunched with a decoy KUDOSITY_API_KEY (tagged; nothing real)
45sclaimed19 tools with a decoy KUDOSITY_API_KEY: send_sms, send_mms, send_whatsapp, get_message, create_webhook, list_webhooks, delete_webhook, get_balance, create_list, get_lists, get_list, add_contact_to_list, remove_contact_from_list, delete_list, list_messages, list_specs, list_endpoints, search_endpoints, get_endpoint
45sprocessscript backend runs setup only
45sprocessno install scripts to re-run

Static findings

No findings across 690 lines in 7 files.

Cost to the agent

Instructions loaded
≈67 tok
1 file · 7 in bundle
Tool list per prompt
≈2,791 tok
19 tools · 147 per tool
Handshake
491 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 99

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 kudosity-mcp@0.5.0 as of 4d ago. This is the package itself, not its dependencies.