# com.tutorializer/tutorializer

Audit localized tutorials and safely maintain project metadata and pronunciation rules.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.1.0
- **Author:** com.tutorializer
- **License:** Unknown
- **Endpoints:** streamable-http https://mcp.tutorializer.com/mcp
- **Source:** https://www.tutorializer.com/developers/#mcp
- **Endpoint health:** reachable (last checked 2026-09-25T21:50:06.410Z, 5 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-25T21:50:06.410Z
- **Version scanned:** live
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

23 declared. Observed from a live `tools/list` probe.
- `list_projects` — List a bounded page of Tutorializer projects the authenticated user has access to. Returns a Markdown table of id, name, domain, and last edit time.
- `get_project` — Fetch a single Tutorializer project by immutable id or stable public vanity id. Returns the project metadata, its locale and voice settings, and any pronunciati
- `get_project_localization_summary` — Audit one Tutorializer project across configured locales, rendered-video locales/devices, and speech languages. Reads at most 100 rows per content type and mark
- `list_tutorials` — List Tutorializer tutorial definitions. Optionally filter by projectId. Returns a Markdown table of id, name, project, default voice, and last edit time; render
- `get_tutorial` — Fetch one Tutorializer tutorial definition and a bounded preview of its rendered locale/device outputs. A tutorial does not itself have a locale or status; thos
- `list_videos` — List rendered Tutorializer videos. Optionally filter by projectId, tutorialId, locale, and device. Returns a Markdown table of output dimensions, locale, device
- `get_video` — Fetch a single rendered Tutorializer video by id. Returns its tutorial, locale, device, dimensions, primary media URL, chapters, subtitles, and thumbnail metada
- `list_speeches` — List a bounded page of Tutorializer speeches (voiceover segments). Optionally filter by projectId and language. Returns a safe preview of id, text, language, pr
- `get_speech` — Fetch a single Tutorializer speech (voiceover segment) by id. Returns the speech metadata plus its full source text and translation formatted as Markdown.
- `create_project` — Create a Tutorializer project. State-changing and non-idempotent: repeating the call creates another project, so list projects and confirm the intended name fir
- `update_project` — Change a Tutorializer project’s name, domain, locales, default voice or narration speed. Reads the stored project first and rewrites the whole record, so unspec
- `create_tutorial` — Create a Tutorializer tutorial definition inside a project. State-changing and non-idempotent: repeating the call creates another tutorial, so list tutorials an
- `update_tutorial` — Rename a Tutorializer tutorial or change the default voice used for its narration. Reads the stored tutorial first and rewrites the whole record, so unspecified
- `create_video` — Register one already-uploaded rendered tutorial video with Tutorializer, recording its locale, device, dimensions and media URLs. State-changing and non-idempot
- `update_video` — Correct the metadata of one registered Tutorializer rendered video, such as its locale, device, dimensions or media URLs. Reads the stored record first and rewr
- `create_speech` — Create one Tutorializer voiceover segment for a project. Without a url it synthesizes narration audio from the text with the project's speech provider, which co
- `update_speech` — Change the text, translation, language or voice of one Tutorializer voiceover segment. Every one of those fields determines the audio, so a real change re-synth
- `set_pronunciation_rule` — Add or replace one project pronunciation rule and synchronize its ElevenLabs pronunciation dictionary. Repeating an identical rule is a no-op.
- `remove_pronunciation_rule` — Remove one project pronunciation rule and synchronize its ElevenLabs dictionary. Destructive but idempotent: a missing rule is a no-op. Existing speech audio is
- `delete_tutorial` — Permanently delete one Tutorializer tutorial definition. Idempotent, but the definition must be authored again to restore it. Rendered videos and voiceover segm
- `delete_speech` — Permanently delete one Tutorializer speech record plus its S3 audio and alignment files. Idempotent, but deleted audio cannot be recovered without synthesizing 
- `delete_video` — Permanently delete one Tutorializer rendered-video record and its primary S3 object. Idempotent, but the render must be uploaded or generated again to restore i
- `show_project_overview` — Render a bounded tenant-scoped Tutorializer project snapshot with tutorial, video, and voiceover counts. Use this after listing projects or when the user provid

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"tutorializer\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.tutorializer.com/mcp\"\n    }\n  }\n}"
```

## Blast radius

Extensive blast radius — deletes data; runs on someone else's infrastructure.
- Floor 35, ceiling 59 (tier: extensive)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/com.tutorializer%2Ftutorializer
- Install plan: https://forgeregistry.com/api/v1/packages/com.tutorializer%2Ftutorializer/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/com.tutorializer%2Ftutorializer
- HTML page: https://forgeregistry.com/registry/com.tutorializer%2Ftutorializer
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.