Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Crixin Voice

NPM · CRIXIN · 2 COMPONENTS

Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted.

−3 this week 79 Trust /100

Last scanned (22 hours ago)

Scores higher than 61% of npm servers

Category Communication

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security88
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known medium-severity CVE affects @hono/node-server 1.19.18, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 34 of 106 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 60 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 839 tokens (~139/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 61% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 1 Nov 26 0
    • Stability: 0.97 → pass security
  • 31 Oct 26 0
    • Stability: pass → 0.97 functional
  • 29 Oct 26 −3
    • CVE-2026-118663 affects this package: medium ▼ security
    • Known CVEs: pass → fail ▼ security
  • 25 Oct 26 0
    • Stability: 0.97 → pass security
  • 24 Oct 26 0
    • Stability: pass → 0.97 functional
  • 18 Oct 26 0
    • Stability: 0.97 → pass security
  • 17 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Analysed npm/crixin@0.7.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-rmxm-3fg6-px4f CVE-2026-118663 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 106 packages
Packages resolved 106
Stale 34
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~839 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_call ~33

Look up a single call by SID. Returns status, duration, price, timestamps.

NameTypeReqDescription
call_sidstringyes–

No output schema declared.

No examples provided.

list_calls ~76

List recent calls. Filter by `to`, `from`, `status`, or `start_time_after` (ISO timestamp).

NameTypeReqDescription
fromstring––
page_sizeinteger––
start_time_afterstring–ISO 8601 timestamp.
statusstring––
tostring––

No output schema declared.

No examples provided.

list_recordings ~39

List recordings attached to a call. Returns SIDs, durations, and direct media URLs (auth-protected).

NameTypeReqDescription
call_sidstringyes–

No output schema declared.

No examples provided.

make_call ~486

Place an outbound voice call through Twilio. Pass a `to` number (E.164 like +201234567890) and either a `prompt` (the assistant will speak it; recipient response is recorded by default) or raw `twiml` for full control. Returns the Call SID and initial status.

NameTypeReqDescription
closing_messagestring–Optional final line spoken before hangup.
consentedboolean–Attest that the recipient has given prior express consent (and, where required by law, prior express WRITTEN consent) to receive this AI voice call. Required for destinations in strict-consent jurisd…
languagestring–Locale tag matching the voice, e.g. 'en-US', 'ar-EG'.
machine_detectionstring–Whether Twilio should detect voicemail. 'DetectMessageEnd' waits for the beep before TwiML runs.
max_recording_secondsinteger––
promptstring–What the assistant should say when the recipient picks up. If `record` is not false, a recording prompt is appended.
recordboolean–Whether to record the recipient's reply after the prompt. Ignored when `twiml` or `url` is supplied.
status_callbackstring–Optional public URL Twilio POSTs to as the call progresses (initiated → ringing → answered → completed).
tostringyesE.164 destination number, e.g. +201234567890
twimlstring–Inline TwiML XML to use instead of the prompt/record flow. If set, `prompt` is ignored.
urlstring–Public URL Twilio fetches for TwiML. Use this only if you need stateful flows. Leave empty to inline TwiML.
voicestring–Twilio TTS voice. e.g. 'Polly.Joanna-Neural' (en-US), 'Polly.Hala-Neural' (ar-EG), 'Polly.Zeina' (ar-MSA), 'Google.en-US-Wavenet-D'. Default Polly.Joanna-Neural.

No output schema declared.

No examples provided.

send_sms ~92

Send an SMS or MMS via Twilio. Pass `media_url` for MMS. Use `messaging_service_sid` for sticky-sender behavior.

NameTypeReqDescription
bodystringyesMessage text. SMS auto-segments past 160 chars.
media_urlstring––
messaging_service_sidstring––
status_callbackstring––
tostringyesE.164 destination

No output schema declared.

No examples provided.

transcribe_call ~113

Transcribe a Twilio recording via Deepgram. Supports Arabic (ar), English (en), Spanish (es), and 30+ other languages. Requires DEEPGRAM_API_KEY in env.

NameTypeReqDescription
diarizeboolean–Detect distinct speakers.
languagestring–ISO 639-1 code, e.g. 'ar', 'en'. Pass 'auto' to detect.
modelstring–Deepgram model name. Default 'nova-2'.
recording_sidstringyes–

No output schema declared.

No examples provided.

Install

How do I install the Crixin Voice MCP server?

Crixin Voice runs locally as an npm package, launched with npx -y crixin. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · crixin

# add to Claude Code
claude mcp add com-crixin-voice -- npx -y crixin
Common questions

What is the Crixin Voice MCP server?

Crixin Voice is an MCP server listed in the public MCP registry as com.crixin/voice. Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted. This page covers its npm package (crixin).

Is the Crixin Voice MCP server safe to use?

Crixin Voice scores 79 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 4 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Crixin Voice MCP server expose?

Crixin Voice exposes 6 tools: make_call, get_call, list_calls, list_recordings, transcribe_call, send_sms. Their descriptions and schemas cost roughly 839 tokens of context every time the server is loaded.

Is the Crixin Voice MCP server still maintained?

Crixin Voice is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Crixin Voice MCP server under?

Crixin Voice declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.