Sleek
by Sleek Design(Community)
Visitor takeaway
58/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Needs category
This listing is missing a primary category, which weakens browse placement and AI recommendation routing.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
19h ago
Catalog metadata was refreshed 19h ago (October 16, 2026).
Description
Describe the app you want and Sleek designs the screens for it. Onboarding, home, checkout, a profile page, whatever the app needs. It builds them as one set so they read like a single app instead of five loose mockups, then shows them in the chat. Open the project link to edit any screen, change the layout or the copy, and export what you make. No design skills required. If you can describe the app, you get screens back in a few minutes.
Capabilities
AI Agent Discovery
Sleek is indexed by Tedix as a structured ai application listing for AI assistants, search crawlers, and users comparing agent-ready apps.
- Sleek has no primary catalog category yet; Tedix treats this as a routing gap for browse and recommendation surfaces.
- Developer: Sleek Design.
- Connector type: AI-Powered App.
- Current connector status: Connected.
- Observed distribution channels: chatgpt.
- Available regions: US, FR, GB, ES, KR, IN.
- Declared capabilities: write or update records when authorized.
Use this page to understand whether Sleek is relevant for general AI app workflows in AI assistants.
For MCP discovery, this listing helps crawlers connect Sleek to tool, resource, prompt, and server-health signals instead of treating it as a generic directory entry.
The canonical Tedix directory URL is https://tedix.dev/apps/sleek/.
Crawlable Profile
Source and availability
Tedix identifies Sleek from Upstream Mcp tool source; Store sources: ChatGPT app store; Distribution: Ecosystem Directory; Tenant install: A platform catalog operator must create or reconcile the base app before tenants can install this entry.. Availability is reported for US, FR, GB, ES, KR, IN.
- ChatGPT app storeAuth required · RELEASED · US, FR, GB, ES, KR, IN
Auth, tools, and actions
Authentication: Requires Login. Sleek is flagged for Can Modify Data. Current MCP inventory reports 11 tools, 0 resources, and 0 prompts.
- Cancel a design run · Repeatable action
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 a project · App action
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 a project · High-impact write action
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.
- Design screens with AI · App action
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 a screen's HTML · Read-only action
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 a design run · Read-only action
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 a project · Read-only action
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 screens · Read-only action
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.
Plus 3 additional actions in the full tool inventory.
Verification freshness
- Catalog synced19h ago (October 16, 2026)
- Connector checked16h ago (October 16, 2026)
- MCP scanned16h ago (October 16, 2026)
- Directory updated16h ago (October 16, 2026)
Publisher Intelligence
Public trust signals for visitors and practical recommendations for publishers. Use this section to understand what Tedix can verify today and what would make the app easier for AI agents to find.
Visitor takeaway
58/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Needs category
This listing is missing a primary category, which weakens browse placement and AI recommendation routing.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
19h ago
Catalog metadata was refreshed 19h ago (October 16, 2026).
Server Statussleek v1.0.1
https://sleek.design/api/mcpLast checked: 16h ago
Server Instructions
Sleek designs mobile app UI with AI. Describe an app and get real, editable screens you can show inline and build the app from. Flow: create_project (or list_projects to reuse one), then design, then screenshot, then share the projectUrl the tools return. That URL is where your user opens, edits, and exports the designs; send it every time, do not just describe what was made. To build the working app, call get_component for each screen and use its HTML as the design source. Send the whole request as ONE design message. The agent plans a screen set together, so a single call for 'onboarding, home, item detail, cart, and profile for a plant shop app' produces a coherent app. Five separate calls produce five unrelated screens and charge for each one. Design runs spend the workspace's AI credits; listing, reading, and rendering are free. Free accounts can try the API with their one-time trial credits (about one design run); sustained use requires the Pro plan or higher ($69/month, or $30/month billed yearly at $360/year, including 20,000 monthly AI credits). One design run at a time per project. On CONFLICT, poll get_design_run until the current run settles (completed or failed), then retry. cancel_design_run asks a run to stop sooner; the project stays locked until the run settles. If a tool returns a URL, send your user there. The API includes one exactly when a human has to act (sign in, upgrade, top up credits), and relaying it is how they unblock you. Auth: connect over OAuth, or send an API key created at https://sleek.design/agents/setup as an "Authorization: Bearer sk_..." header.
Technical Details
Tools(11)
Showing 11 of 11 tools
| Flags | Test | ||||
|---|---|---|---|---|---|
cancel_design_run | 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. | — | Not tested | — | |
create_project | 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. | — | Not tested | — | |
delete_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. | destructive | Not tested | — | |
design | 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. | — | Not tested | — | |
get_component | 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. | read-only | Not tested | — | |
get_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. 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. | read-only | Not tested | — | |
get_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. | read-only | Not tested | — | |
list_components | 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. | read-only | Not tested | — | |
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. | read-only | Not tested | — | |
list_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. | read-only | Not tested | — | |
screenshot | 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. | read-only | Not tested | — |
Discoverability Score
Fair
58 / 100
How easily AI agents can find this app from its current catalog metadata.
- Description quality20/20
- Example prompts0/20
- Keyword coverage0/15
- Category clarity0/5
- Tool metadata20/20
- Visual assets8/20
- Endpoint health10/10
- Data freshness15/15
How to Improve
Add at least 2 example prompts. Prompt examples strongly improve app matching and click-through intent.
Increase keyword coverage (discovery + trigger) to improve retrieval for long-tail queries.
Choose a primary catalog category so visitors and AI agents can route this app into the right browse and recommendation surfaces.
Add at least 2 screenshots that show real workflows to increase confidence and conversion.
Technical Details
- Status
- ENABLED
- Type
- AI-Powered App
- Auth
- Requires Login
- Listed on
- ChatGPT
- Added
- October 15, 2026
- Last synced
- 19h ago
- Last checked
- 16h ago
- Version
- 1.0.1
- Distribution
- Ecosystem Directory