The Mobbin MCP connector routes your AI agent's tool calls to Mobbin's own MCP server through Scalekit. Each user signs in to Mobbin once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 3 tools.
- Tools
- 3
- What they doRead · write · destructive
- 3 · 0 · 03 read0 write0 destructive
- Users sign in with
- OAuth
- OAuth app
- Scalekit's or your own
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the Mobbin MCP connection
In AgentKit > Connections, create a Mobbin MCP connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Scalekit credentials are available for Mobbin MCP server, so you don't need to register an OAuth app.
Authorize a user and make your first call
quickstart.mts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'import { createInterface } from 'node:readline/promises'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'mobbinmcp'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize Mobbin MCP:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'mobbinmcp_search_sections',toolInput: { query: 'YOUR_QUERY' },})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "mobbinmcp"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize Mobbin MCP:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={"query":"YOUR_QUERY"},tool_name="mobbinmcp_search_sections",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user signs in once. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_toolmobbinmcp_search_flowsSearch Mobbin for multi-step user flows (e.g.Read-onlySearchFlows
Search Mobbin for multi-step user flows (e.g. onboarding, checkout) using natural language. Returns flow screens with inline images.
Inputs
platformstringrequired- Platform to search.one of
iosweb querystringrequired- Describe one user journey in plain language â the steps and what you'd see along the way. Be specific; detail helps. Good: "onboarding with personalization steps", "checkout with payment method selection". Avoid: combining multiple flows (search separately), negations, vague style words, disconnected keyword lists. Name a specific app to filter results to it (e.g. "Duolingo onboarding"). Do not include platform (ios/web) â use the dedicated parameter.
image_formatstring- Image format. Use jpg if your client does not support webp.one of
webpjpgdefaultwebp limitinteger- Maximum number of flows to return. Lower limits are recommended to manage context size.default
5 output_destinationstring- What you will do with the results after this call. Choose by what gets made with the results, not by the search itself. When the request does not say, go by where you are running: a coding agent in a repository means `code`, a design tool means `design_tool`, a plain chat host means `chat`. Helps return results in the form the workflow needs. `code`: implement or change UI in a codebase or coded prototype, also when looking up examples to base it on first, e.g. React, Swift, HTML/CSS, v0, Lovable. `design_tool`: recreate or put results on a design canvas, e.g. Figma, Paper, Pen.dev, MagicPath. `doc`: write a report, PRD, spec, audit or slides, e.g. in Notion, Google Docs or Slides. `reference_library`: only when saving is the ask: the user wants the results kept for later in a folder, notes or a Mobbin collection. Looking things up to build, design or write from is NOT this. `chat`: only answer in the conversation; the user has not asked you to build, design, write or save anything. `other`: an unlisted destination, none of the above, e.g. posting the results to Slack or email. MUST be the same across all calls for the same task.one of
codedesign_tooldocreference_librarychatother output_toolstring- The product the results go into next, not a later step, if known, e.g. Figma, Paper, Notion. Product name only. When the results go into more than one product, name the one the user asked for first. Not the search source: Mobbin only when the results go back to Mobbin. Omit when unknown. MUST be the same across all calls for the same task.
pageinteger- Page number for paginating through results. Maximum 20.default
1 task_intentstring- One short sentence summarizing the user's overall task. Helps return more relevant results. Write it in English even when the conversation is in another language. MUST be the same across all calls for the same task. Do NOT include verbatim user messages, conversation history, file contents, or personal data.
mobbinmcp_search_screensSearch Mobbin for UI screens using natural language.Read-onlySearchScreens
Search Mobbin for UI screens using natural language. Returns matching screens with inline images and metadata.
Inputs
platformstringrequired- Platform to searchone of
iosweb querystringrequired- Describe one screen in plain language â the UI elements you'd see and how they relate. Be specific; detail helps. Good: "login screen with biometric authentication", "checkout page with promo code field and Apple Pay button". Avoid: combining multiple screens/intents (search separately), negations ("without ads"), vague style words ("modern", "clean"), disconnected keyword lists. Name a specific app to filter results to it (e.g. "Spotify now-playing screen"). Do not include platform (ios/web) â use the dedicated parameter.
exclude_screen_idsarray- Screen IDs to exclude from results
image_formatstring- Image format. Use jpg if your client does not support webp.one of
webpjpgdefaultwebp limitinteger- Maximum number of screens to return. Higher number of screens returned causes increased context usage.default
20 modestring- Search mode. "standard" returns results with low latency. "deep" uses an AI-powered pipeline that interprets intent and scores each candidate for relevance, keeping the strong matches â ideal for nuanced queries. "fast" is a deprecated alias for "standard" and will be removed in a future version â use "standard" instead.one of
deepstandardfastdefaultdeep output_destinationstring- What you will do with the results after this call. Choose by what gets made with the results, not by the search itself. When the request does not say, go by where you are running: a coding agent in a repository means `code`, a design tool means `design_tool`, a plain chat host means `chat`. Helps return results in the form the workflow needs. `code`: implement or change UI in a codebase or coded prototype, also when looking up examples to base it on first, e.g. React, Swift, HTML/CSS, v0, Lovable. `design_tool`: recreate or put results on a design canvas, e.g. Figma, Paper, Pen.dev, MagicPath. `doc`: write a report, PRD, spec, audit or slides, e.g. in Notion, Google Docs or Slides. `reference_library`: only when saving is the ask: the user wants the results kept for later in a folder, notes or a Mobbin collection. Looking things up to build, design or write from is NOT this. `chat`: only answer in the conversation; the user has not asked you to build, design, write or save anything. `other`: an unlisted destination, none of the above, e.g. posting the results to Slack or email. MUST be the same across all calls for the same task.one of
codedesign_tooldocreference_librarychatother output_toolstring- The product the results go into next, not a later step, if known, e.g. Figma, Paper, Notion. Product name only. When the results go into more than one product, name the one the user asked for first. Not the search source: Mobbin only when the results go back to Mobbin. Omit when unknown. MUST be the same across all calls for the same task.
task_intentstring- One short sentence summarizing the user's overall task. Helps return more relevant results. Write it in English even when the conversation is in another language. MUST be the same across all calls for the same task. Do NOT include verbatim user messages, conversation history, file contents, or personal data.
mobbinmcp_search_sectionsSearch Mobbin for website sections (e.g.Read-onlySearchSections
Search Mobbin for website sections (e.g. About, Pricing, Footer) using natural language. Returns section images from real websites.
Inputs
querystringrequired- Describe one website section in plain language â the content and elements you'd see. Be specific; detail helps. Good: "pricing page with plan comparison table", "hero section with signup form". Avoid: combining multiple sections (search separately), negations, vague style words, disconnected keyword lists.
image_formatstring- Image format. Use jpg if your client does not support webp.one of
webpjpgdefaultwebp limitinteger- Maximum number of sections to return. Higher number of sections returned causes increased context usage.default
20 output_destinationstring- What you will do with the results after this call. Choose by what gets made with the results, not by the search itself. When the request does not say, go by where you are running: a coding agent in a repository means `code`, a design tool means `design_tool`, a plain chat host means `chat`. Helps return results in the form the workflow needs. `code`: implement or change UI in a codebase or coded prototype, also when looking up examples to base it on first, e.g. React, Swift, HTML/CSS, v0, Lovable. `design_tool`: recreate or put results on a design canvas, e.g. Figma, Paper, Pen.dev, MagicPath. `doc`: write a report, PRD, spec, audit or slides, e.g. in Notion, Google Docs or Slides. `reference_library`: only when saving is the ask: the user wants the results kept for later in a folder, notes or a Mobbin collection. Looking things up to build, design or write from is NOT this. `chat`: only answer in the conversation; the user has not asked you to build, design, write or save anything. `other`: an unlisted destination, none of the above, e.g. posting the results to Slack or email. MUST be the same across all calls for the same task.one of
codedesign_tooldocreference_librarychatother output_toolstring- The product the results go into next, not a later step, if known, e.g. Figma, Paper, Notion. Product name only. When the results go into more than one product, name the one the user asked for first. Not the search source: Mobbin only when the results go back to Mobbin. Omit when unknown. MUST be the same across all calls for the same task.
pageinteger- Page number for paginating through results.default
1 task_intentstring- One short sentence summarizing the user's overall task. Helps return more relevant results. Write it in English even when the conversation is in another language. MUST be the same across all calls for the same task. Do NOT include verbatim user messages, conversation history, file contents, or personal data.
No tools match.
