AudoSAFE
Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Audo is a set of audio and video tools for you and your AI assistant: remove noise, enhance voices, transcribe, cut, and more. Pro sound, without the studio.
This repository documents Audo's hosted MCP server at https://audo.ai/mcp. It works over streamable HTTP. Sign-in is OAuth: the first time you use it, your assistant asks you to sign in at audo.ai. The repository also holds the server.json entry for the official MCP Registry, ai.audo/audo.
Add it
Claude Code
claude mcp add --transport http --scope user audo https://audo.ai/mcp
Any MCP client
{
"mcpServers": {
"audo": {
"url": "https://audo.ai/mcp"
}
}
}Setup guides for ChatGPT, Claude, and other assistants: https://audo.ai/setup
Tools
Files and jobs: create_upload, import_file (fetches a direct file URL), list_files, get_file, get_job, get_download, get_transcript, cancel_job, and get_account. Uploaded files are deleted after 24 hours.
Free use and pricing
Every tool has a free part each day, with no payment. Beyond it, you pay per minute of audio, and only for jobs that suc
bf8d809170bdOBSERVED · 2026-10-10Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
Gates applied: no_behavioural_pass, no_license.
bf8d809170bdfull audit observations/trust-audit/mcp-server/audo-ai__audo.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 |
|---|---|---|---|---|---|
| 2026-10-10 | bf8d809170bd | SAFE | B | 88 | first audit |
Questions
What is the Audo MCP server?
Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.
Is Audo safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Audo need?
No credential environment variables were found in its source, so it appears to need none.
How does Audo run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (bf8d809170bd), read on 2026-10-10. The repository is watched and re-audited when it changes.