Mobbin

Search Flows

search_flows

Read-only

Search Mobbin for multi-step user flows (e.g. onboarding, checkout) using natural language. Returns evenly-spaced preview images inline along with metadata for each flow, including per-screen previews. Examine the returned images to understand each flow's actual content — do not describe screens based solely on metadata. Inline images are low-res previews for you to read, not for the user. Each result's image_url is the high-resolution image. Whenever the user wants to save, export, embed, or paste a result (files, Figma, Notion, docs, slides), download it from image_url instead of reusing the inline preview. Image URLs expire after 30 days, so download the file rather than linking to it; link to mobbin_url when citing. On hosts that support MCP Apps, also renders an interactive gallery of the results.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`page`	No	Page number for paginating through results. Maximum 20.
`limit`	No	Maximum number of flows to return. Lower limits are recommended to manage context size.
`query`	Yes	Describe one user journey in plain language — 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) — use the dedicated parameter.
`platform`	Yes	Platform to search.
`output_tool`	No	The product the results go into next, 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_intent`	No	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.
`image_format`	No	Image format. Use jpg if your client does not support webp.	webp
`output_destination`	No	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, 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.

Output Schema

TableJSON Schema

Name	Required	Description
`page`	Yes	1-based page number of search results.
`flows`	Yes
`query`	Yes	The natural language query used for this search.
`has_next_page`	Yes	Whether more pages of results are available.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 24, 2026

addedInput schema / properties / output_destination

Added value: +{
+  "description": "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, 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.",
+  "enum": [
+    "code",
+    "design_tool",
+    "doc",
+    "reference_library",
+    "chat",
+    "other"
+  ],
+  "type": "string"
+}

addedInput schema / properties / output_tool

Added value: +{
+  "description": "The product the results go into next, 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.",
+  "type": "string"
+}

Changed1 schema field changedSep 15, 2026

changedOutput schema / properties / flows / items / properties / screens / items / properties / image_url / description

Previous value: -"Image URL for the screen. Expires after 30 days."New value: +"High-resolution image URL (up to 1920px wide). Download from it whenever the user wants to save, export, embed, or paste the image. Expires after 30 days."

Changed1 schema field changedAug 28, 2026

changedInput schema / properties / task_intent / description

Previous value: -"One short sentence summarizing the user's overall task. Helps return more relevant results. MUST be the same across all calls for the same task. Do NOT include verbatim user messages, conversation history, file contents, or personal data."New value: +"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."

Changed1 schema field changedAug 27, 2026

addedInput schema / properties / task_intent

Added value: +{
+  "description": "One short sentence summarizing the user's overall task. Helps return more relevant results. MUST be the same across all calls for the same task. Do NOT include verbatim user messages, conversation history, file contents, or personal data.",
+  "type": "string"
+}

First observedAug 18, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate a read-only, non-destructive operation, and the description adds substantial behavioral detail beyond that: results include inline low-res previews and per-screen previews, image_url is the high-res source, URLs expire after 30 days, and MCP Apps hosts render an interactive gallery. It also instructs the agent to examine images rather than rely on metadata.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every section earns its place: purpose, image handling, expiry, citing, gallery behavior, and per-parameter guidance. It is not maximally concise, but it is well-organized and front-loads the core purpose before operational details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with an output schema and read-only annotations, the description covers return characteristics, image fidelity, URL expiry, output destinations, and query quality. Nothing the agent needs to decide when to call or how to handle results is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds meaning well beyond the schema. The query parameter gets detailed examples and explicit anti-patterns; output_destination gets a full decision procedure with examples; output_tool and task_intent get consistency requirements. This materially improves correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Search Mobbin for multi-step user flows' — a specific verb, resource, and scope. This distinguishes it from the sibling tools search_screens and search_sections by focusing on multi-step flows with examples like onboarding and checkout.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: natural language queries describing one journey, with strong do's and don'ts in the query parameter (avoid combining flows, negations, vague keywords) and guidance to name a specific app. It does not explicitly name sibling tools as alternatives, but the 'multi-step flows' framing and query guidance make the intended use clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Mobbin tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.