# io.github.farssaadeldin7-ux/podcast-video-studio (mcpb · podcast-video-studio.mcpb)

Turn a long recording into a scored cut list of clips that stand alone, with destinations,...

- Trust score: 36/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- mcpb · `podcast-video-studio.mcpb`: 36/100 (this document), [markdown](https://verifymcp.io/servers/farssaadeldin7-ux-podcast-video-studio/podcast-video-studio.md), [page](https://verifymcp.io/servers/farssaadeldin7-ux-podcast-video-studio/podcast-video-studio)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/podcast-video-studio.mcpb`
- Version: `0.1.3`
- Transport: `stdio`
- SHA-256: `cff6dd749828c97b9fa4bc347df64a179149165196de258b5b0a7ee12c6b1ac0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-25.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1792 tokens (~119/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.farssaadeldin7-ux/podcast-video-studio MCP server?

io.github.farssaadeldin7-ux/podcast-video-studio ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, cff6dd749828c97b9fa4bc347df64a179149165196de258b5b0a7ee12c6b1ac0; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/podcast-video-studio.mcpb`
- SHA-256: `cff6dd749828c97b9fa4bc347df64a179149165196de258b5b0a7ee12c6b1ac0`

### Verify on macOS / Linux

```bash
echo "cff6dd749828c97b9fa4bc347df64a179149165196de258b5b0a7ee12c6b1ac0  podcast-video-studio.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\podcast-video-studio.mcpb).Hash -eq "cff6dd749828c97b9fa4bc347df64a179149165196de258b5b0a7ee12c6b1ac0"
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-21 (score 36)

First indexed and scored.

## MCP tools (15)

### `moment_archetypes` (~83 tokens)

The seven moment archetypes that travel out of a long recording, each with the transcript-level tells for spotting it, typical length, best-fit destinations and what to watch for. Omit archetype to list all seven. Descriptive only — it reads nothing.

Input parameters:

- `archetype` (string): Optional single archetype id, e.g. "contrarian_claim".

### `scoring_rubric` (~82 tokens)

The clip-scoring rubric: four axes with 0–3 band descriptors, the hard disqualifiers applied before scoring, and the threshold table that turns a total into an action. Set include_examples for the four worked scored examples. This returns the rubric — score_clip applies it.

Input parameters:

- `include_examples` (boolean): Also return the four worked scored examples.

### `destination_specs` (~81 tokens)

Length, aspect, frame, safe areas, captions and pacing per destination, plus the cross-posting rules. Omit destination for the at-a-glance table. The numbers are current-generation defaults, not guarantees — platforms change without announcement.

Input parameters:

- `destination` (string): youtube_shorts, instagram_reels, tiktok, linkedin, x or youtube_chapter.

### `scan_candidates` (~105 tokens)

Scan a transcript for the literal archetype tells — "everyone thinks", "say that again", "we went from", and the rest — and return each matched turn with the tells named, the evidence quoted, and the nearest timecode. Matches are candidates for the rubric, not clips, and the scan does not rank or score them. Requires a paid plan.

Input parameters:

- `transcript` (string, required): The transcript text, ideally timecoded and speaker-labelled, verbatim rather than tidied.

### `score_clip` (~259 tokens)

Apply the rubric mechanically to a candidate: disqualifiers first (they remove, they do not deduct), then the four axis scores you have already assigned — self-contained premise, tension, payoff, boundaries, 0–3 each — through the threshold table, including the terminal premise-0 rule and the no-axis-below-2 condition at 9. Pass duration_seconds to also get which destination length bands the clip fits. Arithmetic only — it does not read the segment or assign the scores. Requires a paid plan.

Input parameters:

- `boundaries` (number): Clean boundaries, 0–3.
- `disqualifiers` (array): Disqualifier ids that apply, from: unresolved_referent, payoff_outside_out_point, callback, off_screen_visual, crosstalk_over_key_line, no_clean_in_point, named_third_party, unverifiable_claim. If an…
- `duration_seconds` (number): Optional natural length of the segment, for the destination fit.
- `payoff` (number): Payoff inside the clip, 0–3.
- `premise` (number): Self-contained premise, 0–3.
- `tension` (number): Tension, 0–3.

### `log_clip` (~258 tokens)

Record a threshold-clearing clip in the local log so the footage-pass result can be recorded against it later. The skill budgets for around a third of clips failing that pass; the log replaces the assumption with your own count. Requires a paid plan; the licence check is the only thing this tool sends anywhere.

Input parameters:

- `archetypes` (array): Archetype ids the clip carries.
- `cold_open` (string): The cold-open line, quoted from the clip.
- `destinations` (array): Where it is going, e.g. ["instagram_reels","linkedin"].
- `duration_seconds` (number)
- `episode` (string): Episode name or identifier.
- `flagged_claims` (array): Factual claims in the clip that need sourcing before publish.
- `in_point` (string, required): Timecode of the in-point, e.g. "00:14:22.4".
- `notes` (string)
- `out_point` (string, required): Timecode of the out-point.
- `scores` (object): The four axis scores, e.g. {"premise":3,"tension":3,"payoff":2,"boundaries":3}.
- `total` (number): The rubric total out of 12.

### `record_footage_pass` (~99 tokens)

Record how a logged clip fared in the human footage pass — passed, or failed with the reason the text could not show (framing, audio, expression, crosstalk, an unsafe claim). Requires a paid plan.

Input parameters:

- `clip_id` (string, required)
- `reason` (string): For a failure, what the footage showed that the transcript could not.
- `result` (string, required): One of: passed, failed.

### `review_clips` (~65 tokens)

The record of logged clips and a plain tally of the footage pass — how many cleared the threshold, how many passed on footage, how many failed and why. Counting only; it makes no new claim. Requires a paid plan.

Input parameters:

- `limit` (number): Default 20.

### `cut_clips` (~214 tokens)

Cut clips out of a local media file with ffmpeg. Each clip gets a lossless stream-copy cut (no re-encode), and, where a destination is named, also a destination-formatted variant — scaled and centre-cropped to the frame in destination_specs (9:16 1080×1920 for TikTok, Reels and Shorts). A clip longer than its destination's length band is refused, citing the spec. If ffmpeg is not installed, nothing is cut and the exact per-clip commands are returned ready to run. Reports per clip what ran, what file it produced, and any failure with ffmpeg's own stderr. Requires a paid plan; nothing but the licence check leaves the machine.

Input parameters:

- `clips` (array, required): The clips to cut, from the cut list.
- `out_dir` (string): Where the files go. Default: a "clips" directory next to the source.
- `source` (string, required): Path to the local media file (the episode video or audio).

### `caption_pack` (~165 tokens)

Apply a destination's caption spec to a clip's own transcript: the hook line (the clip's first sentence, verbatim), actual character counts against the field's hard limit and feed truncation point, and the destination's hashtag rule — with any supplied hashtags checked against it. Formatting only: it structures what it is given and never invents copy; the context-or-position line and the tags come back as named slots to fill. Requires a paid plan.

Input parameters:

- `destination` (string, required): youtube_shorts, instagram_reels, tiktok, linkedin, x or youtube_chapter.
- `hashtags` (array): Optional hashtags you intend to use, checked against the destination's rule.
- `transcript` (string, required): The clip's transcript text — just the clip, not the episode.

### `license_status` (~51 tokens)

Check the Podcast & Video Studio licence on this machine: plan, included capabilities, remaining quota and seat usage. Call this when a paid tool reports a licence problem, or when the user asks what their plan includes.

### `license_activate` (~68 tokens)

Store and activate a Podcast & Video Studio licence key on this machine. Use when the user pastes a licence key, or after a purchase completes.

Input parameters:

- `license_key` (string, required): The licence key, e.g. PS-XXX-00000-00000-00000-0000

### `start_checkout` (~75 tokens)

Begin a Podcast & Video Studio purchase. Returns a Stripe Checkout link. Call list_plans first if the user has not chosen a plan.

Input parameters:

- `email` (string): Email address for the receipt and licence.
- `plan` (string, required): Plan id: "pro" or "team". Use list_plans to see the options.

### `list_plans` (~25 tokens)

List the available Podcast & Video Studio plans, prices and what each one includes.

### `billing_portal` (~31 tokens)

Open the Stripe billing portal to change plan, update the card, or cancel the Podcast & Video Studio subscription.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/farssaadeldin7-ux-podcast-video-studio/podcast-video-studio#diagnostics

## Score history

- 2026-10-25: 36
- 2026-10-24: 36
- 2026-10-23: 36
- 2026-10-22: 36
- 2026-10-21: 36

## Common questions

### What is the io.github.farssaadeldin7-ux/podcast-video-studio MCP server?

io.github.farssaadeldin7-ux/podcast-video-studio is an MCP server listed in the public MCP registry as io.github.farssaadeldin7-ux/podcast-video-studio. Turn a long recording into a scored cut list of clips that stand alone, with destinations,... This page covers its MCPB bundle (https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/podcast-video-studio.mcpb).

### Is the io.github.farssaadeldin7-ux/podcast-video-studio MCP server safe to use?

io.github.farssaadeldin7-ux/podcast-video-studio scores 36 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.farssaadeldin7-ux/podcast-video-studio MCP server expose?

io.github.farssaadeldin7-ux/podcast-video-studio exposes 15 tools: moment_archetypes, scoring_rubric, destination_specs, scan_candidates, score_clip, and 10 more. Their descriptions and schemas cost roughly 1,661 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/farssaadeldin7-ux/claude-plugin-suite
- Changelog RSS feed: https://verifymcp.io/servers/farssaadeldin7-ux-podcast-video-studio/podcast-video-studio.xml
- Changelog JSON feed: https://verifymcp.io/servers/farssaadeldin7-ux-podcast-video-studio/podcast-video-studio.json
- HTML version of this page: https://verifymcp.io/servers/farssaadeldin7-ux-podcast-video-studio/podcast-video-studio