Sleek MCP server

• cancel_design_runwrite actionFree

  Ask a design run to stop, for example when the brief was wrong. A queued run never starts. A running run stops at its next step and stays 'running' until it settles. 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 is charged only when that list is not empty. A run that had already finished settles as 'completed'. 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.

• create_projectwrite actionFree

  Create an empty project, then call design and screenshot. Creation is free and instant. Only design runs spend credits. Share projectUrl so your user can watch and edit the designs.

• delete_projectwrite actionFree

  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.

• designwrite actionFree

  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 spends workspace credits 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, your user has to act there, such as topping up credits, before you retry. On completion, share projectUrl with your user and call screenshot.

• get_componentFree

  Fetch a screen's generated HTML. Returns 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_runwrite actionFree

  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 is charged only when the list is not empty. Check it before resending the brief.

• get_projectFree

  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.

• list_componentsFree

  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_projectsFree

  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.

• list_referencesFree

  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.

• screenshotFree

  Render up to four project screens as one inline image, after a design run completes. Rendering is free. Send projectUrl with the image so your user can open and edit the designs.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 5966ms12/20
• Tool poisoning11 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 5 write-action tools with no auth3/15
• Maintenancelast push 0 days ago15/15
• Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10

Safety score

71/100

higher than 38% of 4,460 AI and agents servers

Tools

11

the typical AI and agents server has 6

Tools that change things

45%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote AI and agents server answers 100%

Response time

220 ms

faster than 62% of 2,331 AI and agents servers

Sleek: common questions

Is Sleek MCP server safe?

Mostly: it is graded B (71/100). Read the Sleek safety report

How do I install Sleek?

It runs remotely at sleek.design. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Sleek need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Sleek maintained?

The last commit was 20 days ago (2026-10-15). The latest release is v1.0.1.

Is Sleek up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Sleek?

Servers from other publishers that do the same job: Figma Context MCP server, Serena MCP: the IDE for your agent MCP server and agent-device MCP server.

How does Sleek compare with other AI and agents MCP servers?

safety score 71/100 (higher than 38% of 4,460 AI and agents servers); tools 11 (the typical AI and agents server has 6); tools that change things 45% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.