1
Copy the CleanAudio connector URL
You'll paste this URL into Claude in the next step
Trim audio from an agent, no FFmpeg install
Use CleanAudio's hosted MCP to cut intros, endings, and unwanted sections after you sign in with your CleanAudio account
MCP
2
Go to Claude → Customize
In Claude desktop or claude.ai, go to Customize → Connectors. Name it CleanAudio and paste the URL
3
Connect, sign in and start
Sign in, then ask Claude to clean, cut, or transcribe audio
CleanAudio's audio trimming MCP lets an agent call cut_audio after you connect the hosted URL and sign in. Ask it to trim the first 30 seconds, remove an outro, or make a focused clip without running a local FFmpeg command.
For multi-clip edits, the same connector also offers join_audio, clean_noise, remove_silence, text_to_speech, and transcribe.
What this MCP server does
- Clean background noise with clean_noise
- Cut an uploaded recording with cut_audio
- Join ordered clips with join_audio
- Remove pauses with remove_silence
- Generate speech with text_to_speech
- Create a transcript with transcribe
- Make focused clips with cut_audio
Example prompts
Ask Claude, Cursor, ChatGPT, or VS Code in plain language.
- “Trim the first 30 seconds from this MP3.”
- “Cut the outro from this podcast recording.”
- “Keep only the section after the speaker introduction.”
- “Remove silence, then trim the first 10 seconds.”
- “Clean noise before cutting this clip.”
A prompt-first way to trim recordings
Precise cut requests
Tell your agent which opening, ending, or section should be removed.
No local command chain
CleanAudio hosts the processing service, so setup does not depend on a local FFmpeg binary.
Continue the workflow
After a cut, ask for noise cleanup, silence removal, joining, or a transcript.
Trim an audio file through MCP
Use the hosted connector and describe the cut you want in plain language.
- 1
Copy the hosted connector URL
Copy https://mcp.cleanaudio.app/mcp. CleanAudio hosts the MCP server, so there is no local server or FFmpeg installation.
- 2
Connect your AI agent
Add the URL in Claude Connectors, Cursor Settings → MCP, ChatGPT connectors, or your VS Code MCP client.
- 3
Sign in to CleanAudio
Complete the browser sign-in with your CleanAudio account. Authorization keeps processing and usage tied to your account.
- 4
Ask for an audio trim
Upload or reference your audio, then give the agent a concrete instruction. It can choose the relevant CleanAudio tool.
Tools your agent can call
The hosted connector makes cut_audio available alongside clean_noise, join_audio, remove_silence, text_to_speech, and transcribe.
clean_noise
Remove background noise from podcast recordings
cut_audio
Trim MP3 files to create ringtones or clips
join_audio
Merge multiple audio files into one
text_to_speech
Convert blog posts to audio narration
remove_silence
Clean up long recordings by removing pauses
transcribe
Convert speech to text automatically
Related audio editing MCP workflows
CleanAudio MCP hub
Connect an AI agent to CleanAudio's hosted audio tools.
MCP connector documentation
See setup guidance and the available CleanAudio MCP tools.
Claude MCP for audio
Use the same hosted connector from Claude.
Cursor MCP for audio
Run CleanAudio tools from the Cursor agent.
Audio editing MCP
Explore another focused CleanAudio MCP workflow.
CleanAudio Audio Trimming MCP FAQ
CleanAudio exposes cut_audio for agent-directed trimming and section cuts.
Yes. Ask the agent to cut the opening duration or describe the section to remove.
No. Use the hosted CleanAudio MCP URL and sign in from your agent's connector flow.
Yes. Your agent can call clean_noise and cut_audio as separate steps on the same project.
No separate key is needed for the hosted connector. Authenticate with your CleanAudio account.
Start audio trimming from your agent
Add the hosted CleanAudio MCP connector, sign in once, then send a clear audio request from your preferred agent.