← Back to Podcli

Clip podcasts from
Claude Code

Direct answer

Add Podcli. Tell your agent to clip the episode.

26 local tools for Claude Code, Codex, Cursor, and more.

  • 01AGPL-3.0 · free, no paid tier
  • 02Local-first · files stay on your machine
  • 03No watermark · no monthly minute cap
  • 04CLI + web UI (:3847) + MCP (26 tools)
  • 05Whisper + Remotion captions · Claude or Codex scoring
Updated July 26, 2026 · Nika Siradze
View on GitHubWatch the demoInstall in 30 seconds

You talk to the agent. The agent calls Podcli.

Your agent calls local podcast tools.

You
Natural language
“Find 8 clips.”
Agent
Claude / Codex / Cursor
Picks tools. Runs them.
Podcli MCP
Local process, 26 tools
Transcribe → score → render. Files stay local.

The 26 tools, grouped by stage

The agent picks the path.

Ingest

5 tools
transcribe_podcasttranscribe_startset_videoimport_transcriptparse_transcript

Score

6 tools
suggest_clipsanalyze_energymodify_cliptoggle_clipknowledge_baseclip_history

Render

8 tools
create_clipbatch_create_clipsmanage_presetsupdate_settingsmanage_assetslist_outputsmanage_thumbnail_configmanage_reel

Ops

4 tools
job_statusget_ui_statemanage_envai_cli_status

Integrate

3 tools
manage_integrationsexport_to_davinci_resolvemanage_config

Add Podcli to Claude Code

The MCP config is one block. Same shape for Claude Code, Claude Desktop, and Codex.

// claude_desktop_config.json (same shape for Codex)
{
  "mcpServers": {
    "podcli": {
      "command": "podcli",
      "args": ["mcp"]
    }
  }
}

What you actually say to the agent

Natural language. The agent reads the tool list and figures out the call sequence.

›Transcribe and pick 8 clips.
›Render 9:16 clips with karaoke captions.
›Check clip 4 against history.
›Ban monetization this season.
›Batch process season 3.

Why not just use a generic FFmpeg MCP

Same prompt, two tool surfaces. The agent does less work when the tools speak podcast, not pixels.

Generic FFmpeg MCP
Low-level primitives
trimcropconcatscaleencode
Agent has to invent: where moments are, how to crop a face, what burned-in captions look like, dedupe against past clips.
Podcli MCP
Podcast-clipping primitives
suggest_clipscreate_clipknowledge_baseclip_historyanalyze_energy
Agent reasons about clips, not FFmpeg flags. “Find the 8 best” is one tool call.

Honest limits

The MCP server is podcast-clipping primitives, not a generic video editor.

  • Not a full episode editor (use Descript or a DAW for that).
  • First setup installs a local toolchain; hosted tools are faster on day one.
  • AI clip scoring needs your own Claude or OpenAI key (optional).

Frequently asked

The questions people search before they wire Podcli into their MCP client.

What is the Podcli MCP server?+

A Model Context Protocol server that exposes 26 tools covering the podcast-to-clip pipeline: transcription, AI clip scoring against a knowledge base, face-tracked 9:16 cropping, burned-in captions via Remotion, hardware-accelerated export.

How do I add Podcli to Claude Code?+

Install Podcli (curl -fsSL https://podcli.com/install.sh | sh), then run 'podcli mcp install' for Claude Code, or add a 'podcli' entry running 'podcli mcp' for Claude Desktop.

Does the MCP server upload my podcast files anywhere?+

No. It runs locally as a process the agent talks to. Video, transcript, and renders all stay on your machine. The only optional network calls are to the Claude or Codex API for AI clip scoring.

Is this different from a CLI?+

Yes. The CLI is a fixed command. The MCP server exposes discrete tools the agent composes on demand. Both ship in the same install and you can use either.

What models work with Podcli's MCP server?+

Any MCP-compatible client. Tested with Claude Code, Claude Desktop, and Codex. Any agent that speaks MCP can read the tool list and call it.

Wire Podcli into Claude Code

Clone the repo, run the setup script, then point your MCP client at the built server. Takes about as long as making coffee.

View on GitHubCompare to hosted clippers