Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
Tourwright is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
87/100
trust score
9
tools declared
local
runs on your machine
—
downloads a day
What it does
Turn a script into a narrated product tour video: real browser, captions, voice, MP4.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tourwright-mcp '--' npx -y tourwright mcp
# 2 — ask your agent for something these tools do
# tourwright_guide, tourwright_voices, tourwright_validate and 6 more
Tourwright costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CXAll 1 server
cxmiloxx1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Tourwright as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user tourwright-mcp '--' npx -y tourwright mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take TOURWRIGHT_API_URL (Send jobs to a Tourwright API instead of rendering on this machine), TOURWRIGHT_API_TOKEN (Token for TOURWRIGHT_API_URL) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
The script format (browser walkthroughs and narrated slides), every action, voices and examples. Read it before writing a script.
No parameter schema on file.
Text-to-speech voices available on the server and which engines work. Use a voice whose language matches the script.
No parameter schema on file.
Check the structure of a script (fields, actions, variables) without opening any website: fast, offline. Returns { ok } or the list of errors to fix. To know whether its targets still exist on the live site, use tourwright_check.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| script | yes | The script: an object, or YAML/JSON text. Read tourwright_guide first for the format. | |
| vars | object | no | Values for the script variables ({{name}}): the same script makes a different video per set of values |
Queue a script for rendering. With wait=true (default) it waits until the video is ready and returns its links (and local paths), duration, chapters and captions; otherwise it returns the job id to poll with tourwright_job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| script | yes | The script: an object, or YAML/JSON text. Read tourwright_guide first for the format. | |
| vars | object | no | Values for the script variables ({{name}}): the same script makes a different video per set of values |
| assets | object | no | Files the script refers to by name (images, music, uploads), base64-encoded |
| options | object | no | Render settings that override the script |
| wait | boolean | no | Wait for the video (default true); false returns the job id at once, to poll with tourwright_job |
| waitSeconds | integer | no | How long to wait for the video before returning the job as it is (default 900) |
Status, progress and (when done) the result of a render job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The job id returned by tourwright_render with wait=false |
The render jobs on this server, newest first: id, status, progress and, for finished ones, the links to their videos. Use it to find a video rendered earlier or a job id to delete.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Only jobs with this status |
| limit | integer | no | How many jobs at most (default 20) |
Delete a finished (done or failed) job and its files: the video, subtitles, poster and manifest. A job that is queued or rendering cannot be deleted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The job id, from tourwright_render or tourwright_jobs |
Run a script fast, without voice or video, against the real site (validate only checks its structure). Returns every step that failed (the target it looked for, the page, the targets that page offers) and, when it can tell, the new target for it. For a YAML script given as text it also returns…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| script | yes | The script: an object, or YAML/JSON text. Read tourwright_guide first for the format. | |
| vars | object | no | Values for the script variables ({{name}}): the same script makes a different video per set of values |
Render a script file from this machine (.yaml, .json, .js). Paths inside it resolve next to the file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path of the script file on this machine |
| out | string | no | Output .mp4 path or folder (default: ./videos/<name>/) |
| dryRun | boolean | no | Run the script fast without voice or video, to test it |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Tourwright or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
BTrust score 87 / 100
Release 2.3.0 · scanned 4 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score87
Findings10 threat · 4 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest5331baf48b0bf6bdd8eafa37f37cbc3eddf96ab30ecb93dacae39423bb0870c4
Score vectorthreat 94 → client 87
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (9 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 9 recovered tools are registered only when !remote holds (src/mcp.js:181) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
1 of the 9 recovered tools are registered only when !remote && process.env.TOURWRIGHT_MCP_ALLOW_FILES === 'true' holds (src/mcp.js:197) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
7 tools are registered unconditionally · (1) 1 more only when !remote holds (src/mcp.js:181) · (2) 1 more only when !remote && process.env.TOURWRIGHT_MCP_ALLOW_FILES === 'true' holds (src/mcp.js:197) — typically when a key or option is configured. All 9 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| tourwright_guide | no tags | |
| tourwright_voices | no tags | |
| tourwright_validate | no tags | |
| tourwright_render | no tags | |
| tourwright_job | no tags | |
| tourwright_jobs | no tags | |
| tourwright_delete_job | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| tourwright_check conditional (1) | code-execuntrusted-input | code-exec: parameter "script"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| tourwright_render_file conditional (2) | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest5331baf48b0bf6bd
Scanned2026-11-04
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.3.0. Pin a release below and the command asks for exactly that one.
2.3.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Tourwright can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.