# Recap Studio (mcpb · recap-studio.mcpb)

Render and score one HTML page that explains your work or a topic. Opens offline, no JavaScript.

- Trust score: 34/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- mcpb · `recap-studio.mcpb`: 34/100 (this document), [markdown](https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio.md), [page](https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/Aboudjem/recap-studio/releases/download/v0.6.4/recap-studio.mcpb`
- Transport: `stdio`
- SHA-256: `aed2473c6a548dfd64d6e534a2cbd8b3636d2aa841f399f3391720a788946848`

## 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 2026-11-21.

- **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**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 624 tokens (~56/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 69/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 7% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "deploy_vercel_preview" implies "deploy" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: 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 Recap Studio MCP server?

Recap 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, aed2473c6a548dfd64d6e534a2cbd8b3636d2aa841f399f3391720a788946848; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/Aboudjem/recap-studio/releases/download/v0.6.4/recap-studio.mcpb`
- SHA-256: `aed2473c6a548dfd64d6e534a2cbd8b3636d2aa841f399f3391720a788946848`

### Verify on macOS / Linux

```bash
echo "aed2473c6a548dfd64d6e534a2cbd8b3636d2aa841f399f3391720a788946848  recap-studio.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\recap-studio.mcpb).Hash -eq "aed2473c6a548dfd64d6e534a2cbd8b3636d2aa841f399f3391720a788946848"
```

## 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.

### 2026-11-21 (score 34, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 33, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 32)

First indexed and scored.

## MCP tools (11)

### `create_run_artifact` (~54 tokens)

Persist a Recap Studio artifact under artifacts/<slug>/<filename>. Use for generated content JSON, diagrams, reports.

Input parameters:

- `content` (string, required)
- `filename` (string, required)
- `slug` (string, required)

### `read_run_artifact` (~30 tokens)

Read a previously persisted artifact.

Input parameters:

- `filename` (string, required)
- `slug` (string, required)

### `cache_source` (~68 tokens)

Append a research source to .recap-studio/cache/sources.jsonl. Idempotent on URL hash.

Input parameters:

- `excerpt` (string)
- `publishedAt` (string|null)
- `publisher` (string)
- `summary` (string, required)
- `url` (string, required)

### `generate_mermaid_diagram` (~40 tokens)

Validate a Mermaid diagram source and return a normalized snippet plus required alt text.

Input parameters:

- `alt` (string, required)
- `code` (string, required)

### `render_page_screenshot` (~48 tokens)

(scaffold) Render a screenshot of the given URL using Playwright. Disabled until Playwright is installed locally.

Input parameters:

- `outPath` (string, required)
- `url` (string, required)

### `run_accessibility_scan` (~48 tokens)

(scaffold) Run an axe-core scan against a URL or local HTML snapshot. Disabled until axe is installed.

Input parameters:

- `htmlPath` (string)
- `url` (string)

### `run_lighthouse_summary` (~33 tokens)

(scaffold) Run a Lighthouse summary. Disabled until lighthouse is installed locally.

Input parameters:

- `url` (string, required)

### `deploy_vercel_preview` (~57 tokens)

(stub) Never deploys. Checks that confirmed: true and VERCEL_TOKEN are set, then returns the shell command that deploys a Vercel preview, for you to run yourself.

Input parameters:

- `confirmed` (boolean, required)

### `send_email_draft` (~70 tokens)

(stub) Never sends email. Returns the draft (to, subject, first 200 characters of the body) for you to paste into your mail client.

Input parameters:

- `body` (string, required)
- `confirmed` (boolean, required)
- `subject` (string, required)
- `to` (string, required)

### `validate_content` (~65 tokens)

Run the deterministic validation suite against a content JSON and return a Markdown report, verdict first. Reads artifacts/<slug>/content.json, or the optional path.

Input parameters:

- `path` (string): Optional path to the content JSON, relative to the working directory.
- `slug` (string, required)

### `render_recap_html` (~111 tokens)

Render a RecapPageContent JSON into ONE self-contained, dark-mode HTML file: inlined CSS, zero JavaScript, opens with a double-click offline. Reads artifacts/<slug>/content.json (or the optional path) and writes artifacts/<slug>/recap-<slug>.html. Works in any project and any MCP client.

Input parameters:

- `path` (string): Optional path to the content JSON, relative to the working directory.
- `slug` (string, required)
- `theme` (string)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio#diagnostics

## Score history

- 2026-11-21: 34
- 2026-11-20: 33
- 2026-11-19: 33
- 2026-11-18: 32
- 2026-11-17: 32

## Common questions

### What is the Recap Studio MCP server?

Recap Studio is an MCP server listed in the public MCP registry as io.github.Aboudjem/recap-studio. Render and score one HTML page that explains your work or a topic. Opens offline, no JavaScript. This page covers its MCPB bundle (https://github.com/Aboudjem/recap-studio/releases/download/v0.6.4/recap-studio.mcpb).

### Is the Recap Studio MCP server safe to use?

Recap Studio scores 34 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 Recap Studio MCP server expose?

Recap Studio exposes 11 tools: create_run_artifact, read_run_artifact, cache_source, generate_mermaid_diagram, render_page_screenshot, and 6 more. Their descriptions and schemas cost roughly 624 tokens of context every time the server is loaded.

### What licence is the Recap Studio MCP server under?

Recap Studio declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Recap Studio MCP server?

VerifyMCP ran 12 checks on Recap Studio, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about Recap Studio: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Repository: https://github.com/Aboudjem/recap-studio
- Changelog RSS feed: https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio.xml
- Changelog JSON feed: https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio.json
- HTML version of this page: https://verifymcp.io/servers/aboudjem-recap-studio/recap-studio
