Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
Arc 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.
94/100
trust score
15
downloads a day
local
runs on your machine
322
downloads in 30d
What it does
Author, validate, lay out, render, and diff architecture diagrams as code.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user hudsonkit-arc-mcp '--' npx -y @hudsonkit/arc-mcp
# 2 — ask your agent for something these tools do
# open_live_diagram, open_architecture_review, update_architecture_review and 16 more
Arc costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HUAll 1 server
hudsonkit1 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 Arc 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 hudsonkit-arc-mcp '--' npx -y @hudsonkit/arc-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 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
19 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.
Open an idle architecture view in the Hudson Kit Arc studio. Open the returned liveUrl once; use begin_live_diagram_work before doing diagram work, update_live_diagram for full revisions, and finish_live_diagram_work when that work ends. Keep stable node IDs for continuous motion. Connection…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| title | string | no | Human-readable title for the live architecture |
| baseUrl | string | no | Studio base URL (default: ARC_EDITOR_URL or http://localhost:5188) |
| agent | object | no | Optional display identity for this session; preserves the actual MCP client name, version, and connection ID |
Open a saved architecture review with a baseline diagram and a concrete review question. The liveUrl is a read capability; keep the returned resumeToken private so a later MCP connection can resume after disconnect or restart. Revisions, findings, decisions, and open questions persist atomically…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Initial baseline ArcDiagramData JSON |
| title | string | yes | — |
| question | string | yes | The concrete architecture question this review will answer |
| repository | object | no | — |
| agent | object | no | — |
| baseUrl | string | no | — |
Publish review evidence. Only supplied fields are replaced; omitted fields are preserved. Findings must have stable unique IDs, a severity, and source references (use an empty sources array when evidence is not yet available). Arrays replace their previous contents, and an empty summary clears it.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| summary | string | no | — |
| findings | array | no | — |
| decisions | array | no | — |
| openQuestions | array | no | — |
Resume a saved review using its private author capability after the previous MCP owner disconnects. A live owner cannot be displaced. Restored in-progress work is interrupted; declare new work explicitly. Completed reviews remain read-only and can be reopened for viewing. This connection supplies…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| resumeToken | string | yes | — |
| baseUrl | string | no | — |
| agent | object | no | Optional caller-declared display identity for the resumed author; preserves actual MCP client name, version, and connection ID |
Invalidate the current review viewing link and disconnect its viewers. Returns a replacement liveUrl and streamUrl. This rotates only the read capability; the private author resumeToken remains valid. Only the owning MCP connection may revoke a share.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
| baseUrl | string | no | — |
Declare diagram work before doing it, with a concise summary and optional scope (default canvas). Target existing node IDs or a canvas region where new boxes will appear. Returns workId; always finish that ID with finish_live_diagram_work when done. Only one work item may be active per session.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | Live diagram or architecture review opened or resumed on this connection |
| summary | string | yes | What diagram work you are about to perform; concise, honest, and specific |
| scope | no | Canvas, 1–200 unique existing node IDs, or finite canvas coordinates for a planned region |
Finish the active declared diagram work using its workId. Leaves the view idle and reusable for the next begin/update/finish cycle. Stale, expired, or already finished work IDs are rejected. Use end_live_diagram only when the entire diagram session is complete.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | Live diagram or architecture review opened or resumed on this connection |
| workId | string | yes | Current workId returned by begin_live_diagram_work |
| message | string | no | Short note describing the actual result |
Publish the next full diagram revision. Preserve node IDs for smooth moves and use new IDs for new nodes. During declared work this renews its five-minute lease and preserves its scope; otherwise the view stays idle. Invalid diagrams leave the previous revision intact. Only this MCP connection can…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | Live diagram or architecture review opened or resumed on this connection |
| diagram | object | yes | Next complete ArcDiagramData JSON |
| message | string | no | Short description of the current architecture change |
Mark the entire live architecture session complete, also completing any active declared work. For a reusable idle view use finish_live_diagram_work instead. Ordinary diagrams expire after disconnect; saved architecture reviews remain durable and read-only. Open a new session to continue after…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | Live diagram or architecture review opened or resumed on this connection |
| message | string | no | Short completion note |
Validate an ArcDiagramData document. Returns coded diagnostics — consume by code, apply one supportedFixes entry, re-validate. ok is false while any error-severity diagnostic remains.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Arc diagram JSON object or JSON string |
| severity | string | no | Filter returned diagnostics by severity (default: all) |
Structural diff of two Arc diagrams. Returns a DiagramDelta — added/removed/moved/changed nodes, connector adds/removes/changes (keyed by connector id or from→to), connectorStyles and groups deltas, layoutChanged. Feed it to <ArcDiagram data={head} delta={delta} /> for a diff render.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | object | yes | Base ArcDiagramData JSON object or JSON string |
| head | object | yes | Head ArcDiagramData JSON object or JSON string |
Run Arc auto-layout on a diagram. Pass a full diagram or minimal input (nodeData + connectors + connectorStyles).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| input | object | yes | Full ArcDiagramData or AutoDiagramInput (nodeData, connectors, connectorStyles) |
Render an Arc diagram as monospace ASCII/Unicode box art.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| charset | string | no | Character set (default: unicode) |
| maxWidth | integer | no | Max output width in characters |
Render an Arc diagram as deterministic SVG markup using the package export path.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| theme | string | no | — |
| mode | string | no | Color mode; defaults to the theme default |
| backgroundColor | string | no | CSS background color (defaults to the theme canvas) |
| includeGrid | boolean | no | Render the diagram grid (default: branded themes on, others off) |
| padding | number | no | Padding around the export bounds in px (default: 20) |
| flowTime | number | no | Render flow markers at this route second (disables SMIL animation) |
| animateFlows | boolean | no | Embed SMIL flow animation in the SVG (default: true; ignored when flowTime is set) |
Render an Arc diagram as a PNG via an installed Chrome/Chromium binary. Returns MCP image content plus render metadata. Set ARC_CHROME if Chrome is not on PATH.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| theme | string | no | — |
| mode | string | no | Color mode; defaults to the theme default |
| backgroundColor | string | no | CSS background color (defaults to the theme canvas) |
| includeGrid | boolean | no | Render the diagram grid (default: branded themes on, others off) |
| padding | number | no | Padding around the export bounds in px (default: 20) |
| scale | number | no | Raster scale factor (default: 2, max: 4) |
| flowTime | number | no | Flow route second to freeze into the PNG (default: 0) |
Render diagram flows as a GIF or MP4 artifact. Uses deterministic frame captures through Chrome plus ffmpeg; requires an output path because video payloads are too large for MCP text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| output | string | yes | Destination file path for the GIF or MP4 |
| format | string | no | Output format; inferred from output extension when omitted |
| theme | string | no | — |
| mode | string | no | Color mode; defaults to the theme default |
| backgroundColor | string | no | CSS background color (defaults to the theme canvas) |
| includeGrid | boolean | no | Render the diagram grid (default: branded themes on, others off) |
| padding | number | no | Padding around the export bounds in px (default: 20) |
| scale | number | no | Raster scale factor (default: 2, max: 4) |
| fps | number | no | Frames per second (default: 12 for GIF, 30 for MP4) |
| duration | number | no | Seconds to render (default: one full flow cycle) |
Render an Arc diagram as a React component snippet, iframe embed, or standalone HTML page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| format | string | no | Output format: component (TSX), iframe (embed tag), or html (standalone SVG page). Default: html |
| componentName | string | no | Component function name for format=component (default: ArcDiagramExample) |
| dataName | string | no | Diagram const name for format=component (default: diagram) |
| theme | string | no | — |
| mode | string | no | Color mode; defaults to the theme default |
| interactive | boolean | no | Whether the React component is interactive |
| baseUrl | string | no | Studio base URL for format=iframe (default: ARC_EDITOR_URL or http://localhost:5188) |
| sessionId | string | no | Session id for format=iframe URLs (generated if omitted) |
| title | string | no | HTML document title or iframe title |
| width | no | Iframe width in px or CSS percentage | |
| height | no | Iframe height in px or CSS percentage | |
| backgroundColor | string | no | CSS background color for format=html (defaults to the theme canvas) |
| includeGrid | boolean | no | Render the diagram grid for format=html (default: branded themes on, others off) |
| padding | number | no | Padding around the export bounds in px for format=html (default: 20) |
Convert a valid Arc diagram JSON into a TypeScript module that exports ArcDiagramData.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| exportName | string | no | Const name (default: diagram) |
Generated JSON Schema (draft-07) for ArcDiagramData
| Parameter | Type | Required | Notes |
|---|---|---|---|
| diagram | object | yes | Valid ArcDiagramData JSON |
| sessionId | string | no | Session id (generated if omitted) |
| view | string | no | Guided view id to start on (data.views[].id) — deep-links the player chapter |
| baseUrl | string | no | Studio base URL (default: ARC_EDITOR_URL or http://localhost:5188) |
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 Arc 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: —
ATrust score 94 / 100
Release 0.14.1 · scanned 28 Oct 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 score100
Client score94
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest03ed7fc56796ddc4ad127e19138ae80f1155ac95f4e77024c08ab1db7715a0cd
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest03ed7fc56796ddc4
Scanned2026-10-28
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 0.14.1. Pin a release below and the command asks for exactly that one.
0.14.1
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 Arc 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.