Connect Descript’s MCP server, ask your AI assistant to remove filler words and draft show notes from the transcript, and review the edit in Descript before publishing.
Independent review. Unpaid; no partnership with the tools on this page. Based on public documentation and research. Trademarks identify their owners’ products. Disclosure.
Editorial shortlist
Compare your options.
For editing a podcast against its transcript.
Descript MCP steps do not transfer automatically; confirm exports in the chosen editor. Choose one for editing a reviewed video draft; switching may need setup changes.
Editorial judgment, not a personal-use endorsement or performance score. These are alternatives for the named role, not three required stack components. Vendors did not pay for, request or approve these positions.
Editable story comes before automated clip volume. A lower-ranked option may fit your constraints better; compare the conditions stated on each card before choosing.
Setup and portability: Confirm media rights, output specifications and exports. Do not assume project interchange or equivalent API support.
Reviewed 2026-10-21. This page applies a shared comparison for “editing a reviewed video draft” to the stated task and constraints. It is documentation-based editorial guidance, not three new hands-on tests. We weigh value for the job, distinct capabilities, replacement limits, technical effort and interoperability. Check current plan terms before adopting or switching.
Confirmed = vendor-documented, not Ion-tested. Human and AI-platform steps are proposed roles.
Human approval
You review the edit before publishing.
Watch out for
Keep the human approval step: You review the edit before publishing.
Starter prompt
Goal: Draft a podcast edit and source-checked show notes for human review. Tools involved: Descript, Claude. I will review the edit and publish. Work step by step, show me each draft or proposed change, and wait for my approval before anything is sent, published, signed, filed or changed in a live system.
Assembled from this page’s goal and steps. Paste it into your AI platform and adjust it to your situation.
Descript: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it
What the platform statuses mean
Confirmed: documented access meets the recorded requirements. Inferred: a reviewed note describes a plausible, untested pairing. To verify: a connection or step is unresolved. MCP and API pairings need route-specific evidence; a plugin, CLI or API alone does not prove compatible access, credentials or permissions. These are documentation assessments, not IonBin runtime tests.
What we checked (2026-10-17)
Descript MCP signs in with your Descript login, with no API token, and is scoped to the one Drive you choose. Through it, an assistant can import media, edit with Underlord (for example, “add Studio Sound and remove filler words”), search projects, organize folders, publish to a Descript web link, and track or cancel jobs.
Transcripts export as text, Markdown, HTML, RTF or SRT, which is enough for show notes and chapters. DOCX is unavailable through MCP; the separate API supports it.
Limits. API/MCP rendered downloads require publishing a Descript web link; review access settings and approve that publication first. For an unpublished export, use the Descript app. Also, YouTube URLs can’t be used as import sources, and job history is kept for 30 days. In team workspaces, an admin may need to allow custom connectors first.
Pricing.Descript has a $0 plan. Hobbyist is $16 per person per month billed annually or $24 monthly. Imports consume media minutes and AI edits may consume AI credits.
Set it up
Connect Descript to Claude and pick the Drive that holds your podcast.
Ask for filler-word removal and Studio Sound on the episode.
Have Claude read the transcript and draft show notes and chapter markers.
Open the project in Descript and listen through the edit. Automated cuts sometimes clip a word or a laugh.
Regenerate chapters from the final edit, check timestamps, then separately approve the exact destination and sharing settings before publishing.
Keep the original recording and verify cuts in context: removing a filler or pause can change meaning or pacing. Check speaker names, quotations, links and chapter positions against the finished audio. A transcript draft from before the edit may have stale timestamps. Preserve the job ID while waiting; inspect an existing job before retrying an import or paid edit.