Name: Ezkielyna Audio
Author: ezkielynagroup

Ezkielyna Audio MCP

Text to speech and speech to text from local audio files via the Ezkielyna API (prepaid key).

Grade A Local · stdio API key 3 tools v1.0.0 MIT

No reviews yet by ezkielynagroupnpm Runs on your machine, nothing hosted

96/100

trust score

tools declared

local

runs on your machine

—

downloads a day

What it does

Text to speech and speech to text from local audio files via the Ezkielyna API (prepaid key).

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'EZKIELYNA_API_KEY=${EZKIELYNA_API_KEY}' --transport stdio ezkielyna-audio-mcp '--' npx -y ezkielyna-audio-mcp

# 2 — ask your agent for something these tools do
#   text_to_speech, transcribe_audio, list_audio_models

It needs EZKIELYNA_API_KEY: this reads it from your environment, so export it first.

Ezkielyna Audio costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

ezkielynagroup9 servers

6 categories

All 9 servers

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Ezkielyna Audio as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads EZKIELYNA_API_KEY (Ezkielyna API key (Auto group, or a group that lists the audio models)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx EZKIELYNA_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'EZKIELYNA_API_KEY=${EZKIELYNA_API_KEY}' --transport stdio ezkielyna-audio-mcp '--' npx -y ezkielyna-audio-mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: EZKIELYNA_API_KEY — Ezkielyna API key (Auto group, or a group that lists the audio models). You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

3 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Turns text into speech with the Ezkielyna API and saves the audio file locally (never overwrites).

Parameter	Type	Required	Notes
text	string	yes	The text to speak (max … characters).
model	string	no	TTS model id (default edge-tts). See list_audio_models.
voice	string	no	Voice name for the model, e.g. id-ID-GadisNeural or id-ID-ArdiNeural (edge-tts), Kore (tts-gemini-3.1-flash). Empty = the model's default voice. Passed to the API as given.
format	string	no	Audio format (default mp3). Some models only return MP3; the file extension follows the real audio type.
filename	string	no	Optional file name (no folder). Existing files are never overwritten.

Transcribes a local audio file (mp3, m4a, wav, ogg, opus, webm, flac, aac, mp4; max 25 MB) to text with the Ezkielyna API.

Parameter	Type	Required	Notes
file	string	yes	Absolute path of the audio file, e.g. /Users/me/Downloads/voice-note.ogg.
model	string	no	Speech-to-text model id (default whisper-large-v3). See list_audio_models.
language	string	no	Optional ISO-639-1 language code of the speech, e.g. "id" (Indonesian) or "en". Empty = auto-detect.
response_format	string	no	text (default) or subtitles: srt / vtt.
prompt	string	no	Optional hint with names or terms that appear in the audio (max 500 characters).

Lists text-to-speech and speech-to-text models from the public Ezkielyna price list with prices, key groups and voices.

No parameter schema on file.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Ezkielyna Audio or to call it, at any volume.

ATrust score 96 / 100

Release 1.0.0 · scanned 12 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings0 threat · 1 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digest67c6896e0f6381f4624f61c8684c9d8f6caef273524f611d7c2a0964f958f397

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (3 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
text_to_speech	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
transcribe_audio	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
list_audio_models	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest67c6896e0f6381f4

Scanned2026-11-12

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.