audio-transcriberBLOCK
Transcribe audio into text. Agentic AI supported through MCP Server.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
CLI or API | MCP | Agent
Version: 2.1.0
Documentation — Installation, deployment, and usage across the CLI, Python API, MCP server, and A2A agent are maintained in the official documentation.
Overview
Audio Transcriber is a production-grade Agent and Model Context Protocol (MCP) server des
ecca032fdcbcOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add audio-transcriber -- uvx audio-transcriber
{
"mcpServers": {
"audio-transcriber": {
"command": "uvx",
"args": [
"audio-transcriber"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
health_check | read | return { |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (14)
| **Prompt Injection Defense** | ✅ Built-in | 25+ pattern scanner + jailbreak taxonomy (CONCEPT:AU-OS.config.secrets-authentication) |
module = importlib.import_module(module_name)
return importlib.import_module(module_name)
A2A_URL = os.environ.get("A2A_URL", "http://127.0.0.1:9016/a2a/").bumpversion.cfg
.codespellignore
.pre-commit-config.yaml
.vulture_ignore
mod = importlib.import_module(pkg_name)
mod = importlib.import_module(pkg_name)
mod = importlib.import_module(pkg_name)
raw = base64.b64decode(artifact_b64, validate=True)
yield base64.b64decode(data["audio"])
agent-utilities, pyaudio, faster-whisper, setuptools-rust
Gates applied: instruction_override, no_behavioural_pass.
ecca032fdcbcfull audit observations/trust-audit/mcp-server/knuckles-team__audio-transcriber.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | ecca032fdcbc | BLOCK | D | 69 | first audit |
Questions
What is the audio-transcriber MCP server?
Transcribe audio into text. Agentic AI supported through MCP Server.
What tools does audio-transcriber expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is audio-transcriber safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does audio-transcriber need?
No credential environment variables were found in its source, so it appears to need none.
How does audio-transcriber run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as audio-transcriber.
How current is this page?
The grade is for one exact copy of the source (ecca032fdcbc), read on 2026-10-11. The repository is watched and re-audited when it changes.