# Sleek (remote · sleek.design)

Design your mobile app UI with AI, then have your coding agent build the real app from it.

- Trust score: 90/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `sleek.design`: 90/100 (this document), [markdown](https://verifymcp.io/servers/design-sleek-sleek/api-mcp.md), [page](https://verifymcp.io/servers/design-sleek-sleek/api-mcp)

## Channel facts

- Endpoint: `https://sleek.design/api/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-05.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2664 tokens (~156/item across 17 items; 15 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (93% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the Sleek MCP server?

Sleek is a hosted endpoint at https://sleek.design/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http design-sleek-sleek 'https://sleek.design/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "design-sleek-sleek": {
      "url": "https://sleek.design/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "design-sleek-sleek": {
      "type": "http",
      "url": "https://sleek.design/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.design-sleek-sleek]
url = "https://sleek.design/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "design-sleek-sleek": {
      "type": "remote",
      "url": "https://sleek.design/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add design-sleek-sleek --url 'https://sleek.design/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  design-sleek-sleek:
    url: "https://sleek.design/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "design-sleek-sleek": {
      "Transport": "http",
      "Url": "https://sleek.design/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add design-sleek-sleek -t streamable-http -u 'https://sleek.design/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "design-sleek-sleek": {
      "type": "http",
      "url": "https://sleek.design/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-05 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 86, +3)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_project” rewrote its description, which is the text the model reads
- [security] Tool “design” rewrote its description, which is the text the model reads
- [security] Tool “get_design_run” rewrote its description, which is the text the model reads
- [security] Tool “screenshot” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 178 → 156
- [functional] The server now declares the “resources” capability
- [functional] First check of Capabilities: pass
- [functional] First check of Schema quality: 100
- [functional] New resource “home”
- [functional] New resource “project_view”
- [functional] New tool “get_project_view”
- [functional] New tool “open_sleek”
- [functional] New tool “show_project”

### 2026-10-26 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (15)

### `list_projects` (~67 tokens)

List projects

List the workspace's projects, newest first. Each project holds one app's screens, theme, and design chat. Check here before create_project to avoid duplicates.

Input parameters:

- `limit` (integer): Number of items to return.
- `offset` (integer): Number of items to skip before this page.

Output parameters:

- `data` (array): Items on this page.
- `pagination` (object)

### `create_project` (~81 tokens)

Create a project

Create an empty project. Returns it in data, plus projectUrl. Pass data.id as projectId to design, then call show_project once the run completes. Creating a project is instant and uses no credits. Only design runs do. Share projectUrl so your user can watch and edit the designs.

Input parameters:

- `name` (string, required): Display name for the new project.

Output parameters:

- `data` (object)
- `projectUrl` (string): Open link for the project. Share it with your user.

### `get_project` (~63 tokens)

Get a project

Fetch a project and its projectUrl. Use it to confirm the project exists and share the URL with your user. Use list_components to see its screens.

Input parameters:

- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.

Output parameters:

- `data` (object)
- `projectUrl` (string): Open link for the project. Share it with your user.

### `delete_project` (~93 tokens)

Delete a project

Permanently delete a project and all its screens. Designs cannot be recovered. Call only after your user confirms the exact project by name. Never delete projects to tidy up on your own initiative.

Input parameters:

- `confirm` (boolean, required): Set only after your user confirms this exact project by name. Deletion is irreversible.
- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.

Output parameters:

- `deleted` (boolean): Always true. The project and its screens are gone.
- `projectId` (string): Id of the deleted project.

### `list_components` (~108 tokens)

List screens

List a project's screen names and active version numbers without generated HTML. Pass each item's screenId to design. Pass its id as componentId to get_component or in componentIds to screenshot. Use get_component only when you need a screen's code.

Input parameters:

- `limit` (integer): Number of items to return.
- `offset` (integer): Number of items to skip before this page.
- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.

Output parameters:

- `data` (array): Items on this page.
- `pagination` (object)

### `get_component` (~191 tokens)

Get a screen's HTML

Fetch a screen's generated HTML. Returns the screen in data, with the HTML at data.versions[].code. versions holds only the version the screen currently shows. Use allVersions for the full history, which can be large. The returned screenId is the value design takes. Use this for a build handoff, not to check whether a design run worked.

Input parameters:

- `allVersions` (boolean): Return every stored version instead of just the active one. Payloads grow quickly; leave it off unless you need the history.
- `componentId` (string, required): Component id from an item's id in list_components, or a componentId in a run's data.result.operations. Not a screenId.
- `inlineIcons` (boolean): Inline icons as SVG so the HTML works without loading Iconify.
- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.

Output parameters:

- `data` (object)

### `list_references` (~85 tokens)

List design references

List curated app styles and their preview images. When your user asks for a look such as Airbnb, brutalist, or dark fintech, pass the closest reference's id as referenceId to design. Without a reference, the agent picks a style.

Input parameters:

- `limit` (integer): Number of items to return.
- `offset` (integer): Number of items to skip before this page.

Output parameters:

- `data` (array): Items on this page.
- `pagination` (object)

### `design` (~452 tokens)

Design screens with AI

Run Sleek's design agent to create or edit screens from a plain-language brief. Send the whole request as ONE message, such as 'a food delivery app with onboarding, restaurants, dish detail, cart, tracking, and profile'. The agent plans the screens together, so separate calls produce mismatched screens. A run uses workspace credits only when it completes or saves changes. By default this waits for the run to finish. If it returns 'queued' or 'running', poll get_design_run. Only one run can be active per project. On CONFLICT, poll get_design_run until the run settles, then retry. cancel_design_run stops it sooner. If a failed run has data.error.url, relay data.error.message to your user with that link. They have to act before you retry. On completion, call show_project with data.runId to show your user what the run made, inline. Use screenshot only where your client cannot show apps. Then share projectUrl with your user.

Input parameters:

- `idempotencyKey` (string): Pick a unique key for each new design request, such as a UUID. Reuse it for retries to return the original run instead of starting a second one.
- `imageUrls` (array): HTTPS image URLs for visual input, such as screenshots, logos, or style references.
- `message` (string, required): The full design brief, as one message. Name every screen you want in this single request.
- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.
- `referenceId` (string): Design reference to imitate, from list_references.
- `screenId` (string): Edit this existing screen instead of creating new ones. Use the screenId from list_components, or from a previous run's data.result.operations (via design or get_design_run). It is not the component…
- `wait` (boolean): Wait for the run to finish before returning. The wait is capped at 270 seconds, after which you get status 'running' back and poll get_design_run. Set false to return immediately and poll from the st…

Output parameters:

- `data` (object)
- `projectUrl` (string): Open link for the project. Share it with your user.

### `get_design_run` (~175 tokens)

Get a design run

Poll a run that design returned as 'queued' or 'running'. Wait a few seconds between polls. On 'completed', data.result.operations lists the saved screens and theme changes. Call show_project with this runId to show your user what the run made, inline. Use screenshot only where your client cannot show apps. Then share projectUrl. On 'failed', relay data.error.message to your user, with data.error.url if present. A failed run, including a cancelled one, keeps what it saved in that same list and uses credits only when the list is not empty. Check it before resending the brief.

Input parameters:

- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.
- `runId` (string, required): Run id from data.runId in a design result.

Output parameters:

- `data` (object)
- `projectUrl` (string): Open link for the project. Share it with your user.

### `cancel_design_run` (~230 tokens)

Cancel a design run

Ask a design run to stop, for example when the brief was wrong. Returns the run as it stands right after the request. A queued run comes back 'failed' with error code 'cancelled' and never starts. A running run comes back still 'running' and stops at its next step. A run cut short settles as 'failed' with error code 'cancelled', or 'execution_failed' if saving its changes failed. It keeps any screens and theme changes it saved, listed in data.result.operations, and uses credits only when that list is not empty. A run that finishes before it stops settles as 'completed'. A run that had already settled comes back unchanged. The project stays locked until the run settles, so poll get_design_run before starting another run. A run that stopped responding settles as 'failed' with error code 'execution_timeout' 15 minutes after creation.

Input parameters:

- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.
- `runId` (string, required): Run id from data.runId in a design result.

Output parameters:

- `data` (object)
- `projectUrl` (string): Open link for the project. Share it with your user.

### `screenshot` (~286 tokens)

Render screens to an image

Render up to four project screens side by side as one inline image, for clients that cannot show apps. Where your client can, call show_project instead. Returns the image, PNG unless format asks for WebP, and a one-line text note. Rendering uses no credits. Send projectUrl with the image so your user can open and edit the designs.

Input parameters:

- `background` (string): CSS background behind the frames, such as "#ffffff" or "transparent".
- `componentIds` (array, required): Component id from an item's id in list_components, or a componentId in a run's data.result.operations. Not a screenId. Screens render left to right. Render more than 4 in separate calls.
- `format` (string): Image encoding for the screenshot.
- `fullHeight` (boolean): Expand each frame to the full height of its content before capturing, so scrollable screens are rendered fully extended rather than cut off at the bottom of the frame. Frames are capped at 4x the def…
- `padding` (integer): Space in pixels on each side of the row of frames.
- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.
- `scale` (integer): Pixel density. 1 is right for showing a design in chat; raise it only when the user asked for a high-resolution export.

### `show_project` (~145 tokens)

Show a project's screens

Shows your user a project's screens inline, in canvas order. They can enlarge a screen, add screens to this chat, and open the project in Sleek. After a design run completes, call it with that runId to show what the run made. Where the client cannot show apps, this returns the screen names only; use screenshot to see the screens. Returns the screen names and ids, the same ones design takes as screenId.

Input parameters:

- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.
- `runId` (string): Run id from data.runId in a design result. Marks the screens that run changed.

Output parameters:

- `name` (string): Project name.
- `projectId` (string): The project's id.
- `projectUrl` (string): Open link for the project. Share it with your user.
- `runStatus` (string): Status of the run named by runId, when one was given.
- `screenCount` (integer): How many screens the project has, including any not listed.
- `screens` (array): The project's screens in canvas order, up to 200. Every screen the runId run changed is listed.

### `search_mentions` (~73 tokens)

Search projects to mention

Find the workspace's projects by name for an @ mention, newest first. Each item is a resource link whose name is the projectId and whose uri is the projectUrl. To browse every project, use list_projects.

Input parameters:

- `query` (string, required): Text the project name contains, ignoring case. Empty returns the newest projects.

Output parameters:

- `items` (array): Matching projects.

### `get_project_view` (~127 tokens)

Load a project's screen viewer

Called by Sleek's screen viewer to load a project's screens, in canvas order, with their images and the viewer's text. To read screens yourself, use list_components.

Input parameters:

- `locale` (string): The host's BCP 47 locale, such as pt-BR. The viewer's text uses it when Sleek supports that language.
- `projectId` (string, required): Project id from an item's id in list_projects, or data.id in create_project.
- `runId` (string): Run id from data.runId in a design result. Marks the screens that run changed.

Output parameters:

- `name` (string): Project name.
- `projectId` (string): The project's id.
- `projectUrl` (string): Open link for the project. Share it with your user.
- `runStatus` (string): Status of the run named by runId, when one was given.
- `screenCount` (integer): How many screens the project has, including any not listed.
- `screens` (array): The project's screens in canvas order, up to 200. Every screen the runId run changed is listed.

### `open_sleek` (~77 tokens)

Sleek

Called by ChatGPT's sidebar and Sleek's widget to show the workspace's newest projects, each with a cover. To list projects yourself, use list_projects.

Input parameters:

- `locale` (string): The host's BCP 47 locale, such as pt-BR. The sidebar's text uses it when Sleek supports that language.

Output parameters:

- `projects` (array): The workspace's newest projects, newest first.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/design-sleek-sleek/api-mcp#diagnostics

## Score history

- 2026-11-05: 90
- 2026-11-04: 89
- 2026-11-03: 89
- 2026-11-02: 88
- 2026-11-01: 88
- 2026-10-31: 87
- 2026-10-30: 87
- 2026-10-29: 87
- 2026-10-28: 86
- 2026-10-27: 86
- 2026-10-26: 83
- 2026-10-25: 82
- 2026-10-24: 82
- 2026-10-23: 82
- 2026-10-22: 81
- 2026-10-21: 81
- 2026-10-20: 80
- 2026-10-19: 79
- 2026-10-18: 79
- 2026-10-17: 79
- 2026-10-16: 78
- 2026-10-15: 78

## Common questions

### What is the Sleek MCP server?

Sleek is an MCP server listed in the public MCP registry as design.sleek/sleek. Design your mobile app UI with AI, then have your coding agent build the real app from it. This page covers its hosted endpoint (https://sleek.design/api/mcp).

### Is the Sleek MCP server safe to use?

Sleek scores 90 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 Sleek MCP server expose?

Sleek exposes 15 tools: list_projects, create_project, get_project, delete_project, list_components, and 10 more. Their descriptions and schemas cost roughly 2,253 tokens of context every time the server is loaded.

### Does the Sleek MCP server require authentication?

Yes. Sleek asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Sleek MCP server still maintained?

Sleek is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://sleek.design/api/mcp
- Repository: https://github.com/sleekdotdesign/mcp
- Website: https://sleek.design/agents
- Changelog RSS feed: https://verifymcp.io/servers/design-sleek-sleek/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/design-sleek-sleek/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/design-sleek-sleek/api-mcp