Skip to content
mcp/skillhub

Sleek MCP Server

by sleekdotdesigndesign.sleek/sleekv1.0.1

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

0remoteofficial registry

context tax

~2,739 tok/turn11 tools

security

100/100

cold start

hosted

freshness

Active3d ago

Our reading of Sleek, from the data

Sleek is a design MCP server from sleekdotdesign, listed in the official MCP Registry.

Its 11 tools add about 2,762 tokens to every model turn, heavier than the design median of 1,708 tokens across 42 measured servers (measured 2026-10-19).

Maintenance is active: the last public signal was 3 days ago (2026-10-15). For comparison, 70% of design servers are active or maintained.

With 0 GitHub stars it ranks #278 of 696 design servers we index.

It runs as a hosted endpoint, so there is nothing to install.

Install Sleek MCP server

Install in Claude Code

claude mcp add --transport http sleekdotdesign https://sleek.design/api/mcp

Remote endpoints

  • streamable-httphttps://sleek.design/api/mcp

Context tax

Connecting this server adds ~2,762 tokens of tool definitions to every model turn (moderate, 11 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure

ModelPer 1,000 turnsWith prompt caching
Claude Opus 5.5$11.05$0.552
Claude Sonnet 5.5$5.52$0.552
Claude Haiku 5.5$0.276—

Input prices as of 2026-10-06. Excludes your own prompt and output.

Tools (11)

  • design522 tok

    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_

  • screenshot408 tok

    Render up to four project screens side by side as one inline image, after a design run completes. 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.

  • cancel_design_run280 tok

    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

  • get_component245 tok

    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.

  • get_design_run199 tok

    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. Share projectUrl and call screenshot. On 'failed', read data.error.message and send your user to 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.

  • list_components177 tok

    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.

  • list_references145 tok

    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.

  • delete_project137 tok

    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.

  • list_projects127 tok

    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.

  • create_project119 tok

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

  • get_project97 tok

    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.

Security signals

100/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.

Deductions

No findings from the checks that ran.

Checks

  • ✓Repository hygiene (archived, activity, license, security policy)
  • ✓Tool descriptions (prompt-injection and hidden-text heuristics)
  • ○Package metadata (install scripts, provenance) — pending
  • ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending

Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules

Freshness

Active — last maintenance signal 3d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-10-15 · 3d ago · GitHub

  2. Latest release

    no data · GitHub

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-10-15 · 3d ago · official registry · v1.0.1

How it compares in Design

Against the most-starred design servers we index. Token cost is per model turn, measured from each server's live tool list.

ServerStarsToolsTokens / turnFreshnessRuns
Sleek (this)0112,739Activehosted
Figma Developer16,007—not measuredSlowinglocal
Design System11,774—not measuredActivelocal
Magic6,105—not measuredMaintained—
Primer3,918—not measuredActivelocal
Dembrandt3,722—not measuredActivelocal
All design MCP servers

FAQ

›How do I install the Sleek MCP server in Claude Code?

Run: claude mcp add --transport http sleekdotdesign https://sleek.design/api/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Sleek require an API key?

No required environment variables are declared in its published metadata.

›Can I use Sleek as a remote (hosted) MCP server?

Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.

›Is Sleek in the official MCP registry?

Yes, as design.sleek/sleek.

›How many tokens does Sleek add to my context?

Its tool definitions total about 2,739 tokens, resent on every turn.

Sources and method

Official MCP Registry entry
updated 2026-10-15
GitHub repository
fetched 2026-10-19
Last checked against all sources
2026-10-19

The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.

Alternatives to Sleek

Other design MCP servers.

View all