Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
Echo UI 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.
93/100
tool-list score
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
A tactile React component library, and the design system that keeps your AI agent on-brand.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http echo-ui-mcp https://mcp.echo-ui.com/mcp
# 2 — ask your agent for something these tools do
# search_components, get_component, get_tokens and 7 more
Echo UI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
EUAll 1 server
echo-ui1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http echo-ui-mcp https://mcp.echo-ui.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
10 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.
Find the Echo UI item for a job ("a settings toggle", "confirm a delete") or by name. Leads with the best fit, or says plainly that Echo has nothing for the job yet, then lists every match with its install command. The cheapest way to find out what exists, and the first call before writing Echo code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | A job in plain words, or a name. Omit to list everything. |
The full record for one component: description, install command, usage (imports + smallest working snippet), composition (part tree), examples, accessibility, motion & sound, prop table and anti-patterns. It's for before writing code that uses the component: the anti-patterns are the part a model gets wrong from priors.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Registry name ("echo-hardware-button"), bare name ("hardware-button") or title ("HardwareButton"). |
The token families: Layer-3 semantic colour roles (--echo-*), sound names, motion's whole vocabulary — the motion tokens, the spring presets, the morph feels and the CSS duration and ease steps — and the shadow recipes. Any name a component's record lists under Motion is here. Echo components are styled and moved only through these: a hex, a duration or a shadow written by hand, or a token name th
No parameter schema on file.
Just the usage examples for one component, without the rest of its record. For when the component is already chosen and only its calling convention is needed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Registry name, bare name or title. |
The accessibility rules a consumer of Echo can still get wrong — names on controls, form errors, announcements, focus and target size — and, with a name, what that component's accessibility was actually tested against. Echo guarantees WCAG 2.2 AA; this is the part the guarantee cannot cover for you. It's for before building a form, a dialog or anything icon-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | A component, for its own tested/untested record. Omit for the rules that apply everywhere. |
Echo's check on a piece of code you've written or are about to write: colours, spacing, radii, shadows and timing off Echo's scales, raw elements where Echo has the component, props a component doesn't take, controls without a name, markup a keyboard or screen reader can't use, restyling Echo from outside, and the screen rules one file can show. The same rules as npx echo-ui-cli check, which run
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | The file's contents: TSX, JSX or CSS, up to 200,000 characters. |
| file | string | no | Its file name, e.g. "app/settings/page.tsx" or "styles.css", which says what it is. TSX when left out. |
Echo's own styles, the looks Echo publishes, each with its one line and its fingerprint on the seven axes styles are placed on; or, with a name, one of them in full: its settings, rules, refusals, fonts, decisions and the slop police's word. The builder's own styles aren't here: they're in their library or the conversation, and fit_styles weighs them with Echo's.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | One of Echo's styles, e.g. "echo". Omit to list them all. |
Style Fit's shortlist: Echo's styles, and the builder's own passed in, measured against where a product sits on the seven axes (warmth, volume, density, formality, era, craft, ornament) and put in order: a style that misses a locked axis last, then least past tolerance first, then nearest. The same arithmetic as npx echo-ui-cli style fit. It orders; it doesn't pick.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| profile | string | yes | Where the product sits, 1 to 5 on each axis: "W4 V2 D1 F2 E3 C3 O3". |
| tolerance | string | no | How far a style may drift on each axis, 0 (locked) to 4: "W1 V1 D1 F0 E2 C1 O1". Left out, every axis may drift a point. |
| yours | array | no | The builder's own styles, from their library or this conversation. |
Whether a style.json is one Echo can apply, as npx echo-ui-cli style check says it: what stops it, the device it makes (light or dark), what the theme corrects for AA contrast, what the slop police stops (with the question for the builder) or the builder kept, and the decisions it leaves open.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| style | object | yes | The style.json's contents, as a JSON object. |
What a style gives a project: a link that makes the whole Echo site wear its colours, the commands that put it in a project, and, for a project without a terminal, its theme CSS and a DESIGN.md with its rules. One of Echo's styles by name, or the builder's own style.json. A style the slop police stops isn't worn; the answer says what to ask the builder.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | One of Echo's styles, e.g. "echo". |
| style | object | no | The builder's own style.json, as a JSON object. |
| files | boolean | no | Include the theme CSS and DESIGN.md (the default). False when the builder will run the command in a project, which writes both itself. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Echo UI 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: —
ATool-list grade · score 93 / 100
Release 0.3.5 · scanned 7 Nov 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest4a50fc1efa8af100cdf4647563d44c95e3a5b837faabf1d1666729ae03747208
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_components | no tags | |
| get_component | no tags | |
| get_tokens | sensitive-source | sensitive-source: keyword "get_token" |
| get_examples | no tags | |
| get_accessibility | no tags | |
| check_code | no tags | |
| list_styles | no tags | |
| fit_styles | no tags | |
| check_style | no tags | |
| wear_style | 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.
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 digest4a50fc1efa8af100
Scanned2026-11-07
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.3.5.
0.3.5
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 Echo UI 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.