Skip to main content
Glama

Mobbin

by com.mobbin
OverviewDiscussionsAdmin

Server Details

Search real-world UI & UX design references for mobile apps, web apps, and websites with Mobbin.

Ownership verified
Status
Healthy
Uptime
99.9% over 64 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
mobbin/mobbin-mcp-server
GitHub Stars
58
Server Listing
Mobbin MCP Server

TDQS

A4.1/5.0

Scored across 3 tools

Disambiguation4/5

The three tools target distinct content types — multi-step flows, individual UI screens, and website sections — which are mostly easy to tell apart. There is mild conceptual overlap (a flow contains screens, and sections can resemble screens), but the descriptions clarify the boundaries well enough.

Naming Consistency5/5

All three tools follow a perfectly consistent verb_noun pattern (search_flows, search_screens, search_sections). The shared 'search_' prefix makes the family relationship obvious and predictable.

Tool Count4/5

Three tools is on the lean side but reasonable for a focused search-driven design-inspiration service. Each tool maps to a genuine content category, so none feels redundant or unearned.

Completeness3/5

The surface covers search across three content types but offers no retrieval by ID, browsing, or collection operations. For a reference library, the lack of any direct get/lookup tool is a notable gap that limits non-search workflows.

Available Tools

3 tools
search_flowsSearch FlowsA
Read-only
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
pageNoPage number for paginating through results. Maximum 20.
limitNoMaximum number of flows to return. Lower limits are recommended to manage context size.
queryYesDescribe 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.
platformYesPlatform to search.
output_toolNoThe 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_intentNoOne 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_formatNoImage format. Use jpg if your client does not support webp.webp
output_destinationNoWhat 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.

Output Schema

ParametersJSON Schema
NameRequiredDescription
pageYes1-based page number of search results.
flowsYes
queryYesThe natural language query used for this search.
has_next_pageYesWhether more pages of results are available.

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the readOnly/destructive annotations: inline images are low-res previews meant for the agent, `image_url` holds the high-res version, URLs expire after 30 days so files must be downloaded rather than hot-linked, and `mobbin_url` is the citation target. It also discloses that an interactive gallery renders on MCP Apps hosts.

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?

Purpose is front-loaded in the first sentence, followed by a logical sequence: previews, high-res download, expiry, citation, gallery. It is long at roughly eight sentences, but each one carries a distinct instruction about handling the returned images.

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

Completeness4/5

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

For a search tool with an output schema, annotations and a fully documented 8-parameter schema, the definition covers result handling completely. The only missing piece is explicit sibling routing against search_screens and search_sections, which nothing else in the structured data supplies.

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

Parameters3/5

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

Schema description coverage is 100% and the schema already documents query, platform, output_tool, task_intent and output_destination in depth, so the baseline is 3. The description adds return-field names (`image_url`, `mobbin_url`) but no parameter semantics beyond what the schema supplies.

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

Purpose4/5

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

States a specific verb and resource ('Search Mobbin for multi-step user flows') with concrete examples (onboarding, checkout), so the agent knows exactly what comes back. It does not explicitly differentiate itself from the siblings search_screens and search_sections, leaving the flows-vs-screens routing to inference.

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?

Gives clear operational context: use natural language, examine returned images rather than trusting metadata, and download from `image_url` whenever the user wants to save, export, embed or paste. It never states when to prefer this tool over search_screens or search_sections, which is the main gap.

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

search_screensSearch ScreensA
Read-only
Inspect

Search Mobbin for UI screens using natural language. Returns matching screens with inline images and metadata. Examine the returned images to understand each screen's actual content — do not describe or summarize screens based solely on metadata. Each screen has a mobbin_url — the canonical Mobbin link for that screen. When you present results to the user, ALWAYS cite each screen you mention as a markdown link to its mobbin_url so the user can open it on Mobbin. 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. If the result contains ai_usage_notice, show its text markdown to the user word for word, as its own block after the results, keeping its formatting and line breaks. Do not paraphrase, shorten, or merge it with other text. On hosts that support MCP Apps, also renders an interactive gallery of the results.

ParametersJSON Schema
NameRequiredDescriptionDefault
modeNoSearch 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 — ideal for nuanced queries. "fast" is a deprecated alias for "standard" and will be removed in a future version — use "standard" instead.deep
limitNoMaximum number of screens to return. Higher number of screens returned causes increased context usage.
queryYesDescribe one screen in plain language — 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) — use the dedicated parameter.
platformYesPlatform to search
output_toolNoThe 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_intentNoOne 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_formatNoImage format. Use jpg if your client does not support webp.webp
exclude_screen_idsNoScreen IDs to exclude from results
output_destinationNoWhat 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.

Output Schema

ParametersJSON Schema
NameRequiredDescription
queryYesThe natural language query used for this search.
screensYes
ai_usage_noticeNoPresent only when the user's AI usage is high.

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare this is a safe, read-only, closed-world call, and the description adds substantial behavior beyond them: inline images are low-res previews only, `image_url` is the high-res asset, image URLs expire after 30 days, and results may carry an `ai_usage_notice` that must be echoed verbatim. It even discloses that MCP Apps hosts render an interactive gallery.

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?

Front-loaded with purpose and return shape, then ordered instructions; every sentence carries an actionable directive rather than filler. It is dense and runs as a single long paragraph, which slightly hurts scanability for a 9-parameter tool.

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?

An output schema exists, so return-value explanation is unnecessary, and the description instead covers the tricky parts an agent would otherwise get wrong: asset type selection, link expiry, citation format, and verbatim notice handling. Given the tool's complexity, nothing essential is missing.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already carries full parameter documentation, including mode, limit, query heuristics, platform, output_tool and output_destination. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ("Search Mobbin for UI screens using natural language") plus the return format ("matching screens with inline images and metadata"). The resource is distinct from the sibling tools' resources (flows, sections), so an agent can disambiguate without opening schemas.

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?

Gives strong contextual guidance on result handling (cite `mobbin_url`, download from `image_url`, do not reuse inline previews, surface `ai_usage_notice` verbatim), which is clear usage direction. It does not, however, name the sibling alternatives (search_flows, search_sections) or state when to prefer them, so it falls short of explicit alternative routing.

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

search_sectionsSearch SectionsA
Read-only
Inspect

Search Mobbin for website sections (e.g. About, Pricing, Footer) using natural language. Returns section images inline along with metadata. Examine the returned images to understand each section's actual content — do not describe or summarize sections 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.

ParametersJSON Schema
NameRequiredDescriptionDefault
pageNoPage number for paginating through results.
limitNoMaximum number of sections to return. Higher number of sections returned causes increased context usage.
queryYesDescribe one website section in plain language — 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.
output_toolNoThe 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_intentNoOne 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_formatNoImage format. Use jpg if your client does not support webp.webp
output_destinationNoWhat 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.

Output Schema

ParametersJSON Schema
NameRequiredDescription
pageYes1-based page number of this batch of search results.
queryYesThe natural language query used for this search.
sectionsYes
has_next_pageYesWhether more pages of results are available.

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the readOnly/non-destructive annotations: inline images are low-res previews not for the user, `image_url` is the high-res asset, URLs expire after 30 days so files must be downloaded rather than linked, and the tool renders an interactive gallery on MCP Apps hosts. These are real behavioral traits an agent could not infer from structured fields.

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?

Front-loaded with purpose, then image-handling rules in a logical order. Every sentence carries an actionable constraint, though the image preview/high-res/expiry points are restated enough to feel slightly dense.

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?

With an output schema present and annotations covering the safety profile, the description fills exactly the gaps that matter: the preview-vs-hi-res distinction, expiry and download behavior, citation practice, and host-dependent gallery rendering. Nothing needed to call or consume the tool correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100%, so all seven parameters are already documented in the schema (including task_intent and output_destination semantics). The description adds no additional parameter-level meaning, so the baseline 3 applies; its references to `image_url`/`mobbin_url` are outputs, not inputs.

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

Purpose4/5

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

States a specific verb and resource ('Search Mobbin for website sections') and clarifies the target with concrete examples (About, Pricing, Footer). The resource noun 'sections' implicitly separates it from search_screens and search_flows, though it never names those siblings explicitly.

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

Usage Guidelines3/5

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

Strong guidance on how to consume results (read inline images, download from `image_url`, link to `mobbin_url`), but no explicit statement of when to choose this over search_screens or search_flows. Usage context is implied by the resource type rather than stated.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updates
    • Changedsearch_flows2 fields changed
      • changedInput schema / properties / output_destination / description
        Previous value: -"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."New value: +"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."
      • changedInput schema / properties / output_tool / description
        Previous value: -"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."New value: +"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."
    • Changedsearch_screens2 fields changed
      • changedInput schema / properties / output_destination / description
        Previous value: -"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."New value: +"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."
      • changedInput schema / properties / output_tool / description
        Previous value: -"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."New value: +"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."
    • Changedsearch_sections2 fields changed
      • changedInput schema / properties / output_destination / description
        Previous value: -"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."New value: +"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."
      • changedInput schema / properties / output_tool / description
        Previous value: -"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."New value: +"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."
  2. 1 tool update
    • Changedsearch_screens5 fields changed
      • addedOutput schema / properties / ai_usage_notice / additionalProperties
        Added value: +false
      • changedOutput schema / properties / ai_usage_notice / description
        Previous value: -"Present only when the user's AI usage is high. Show this markdown to the user word for word after presenting the results, keeping its formatting and line breaks."New value: +"Present only when the user's AI usage is high."
      • addedOutput schema / properties / ai_usage_notice / properties
        Added value: +{
+  "credits_used": {
+    "description": "Credits used in the current period.",
+    "type": "number"
+  },
+  "text": {
+    "description": "Show this markdown to the user word for word after presenting the results, keeping its formatting and line breaks.",
+    "type": "string"
+  }
+}
      • addedOutput schema / properties / ai_usage_notice / required
        Added value: +[
+  "text",
+  "credits_used"
+]
      • changedOutput schema / properties / ai_usage_notice / type
        Previous value: -"string"New value: +"object"
  3. 1 tool update
    • Changedsearch_screens1 field changed
      • addedOutput schema / properties / ai_usage_notice
        Added value: +{
+  "description": "Present only when the user's AI usage is high. Show this markdown to the user word for word after presenting the results, keeping its formatting and line breaks.",
+  "type": "string"
+}
  4. 3 tool updates
    • Changedsearch_flows2 fields changed
      • 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"
+}
    • Changedsearch_screens2 fields changed
      • 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"
+}
    • Changedsearch_sections2 fields changed
      • 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"
+}
  5. 3 tool updates
    • Changedsearch_flows1 field changed
      • 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."
    • Changedsearch_screens1 field changed
      • changedOutput schema / 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."
    • Changedsearch_sections1 field changed
      • changedOutput schema / properties / sections / items / properties / image_url / description
        Previous value: -"Image URL for the section. 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."
  6. 3 tool updates
    • Changedsearch_flows1 field changed
      • 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."
    • Changedsearch_screens1 field changed
      • 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."
    • Changedsearch_sections1 field changed
      • 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."
  7. 3 tool updates
    • Changedsearch_flows1 field changed
      • 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"
+}
    • Changedsearch_screens1 field changed
      • 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"
+}
    • Changedsearch_sections1 field changed
      • 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"
+}
  8. 3 tool updates
    • First observedsearch_flows
    • First observedsearch_screens
    • First observedsearch_sections

Publisher details

Operator
Mobbin · Publisher source
Operator website
https://mobbin.com
Vendor relationship
First-party
Documentation
https://docs.mobbin.com
Trust center
https://trust.mobbin.com/
Restrictions
Unknown

Related MCP Connectors

Related MCP Servers

  • AllGoodInsp

    SawadaGoki
    A
    license
    Not graded
    quality
    C
    maintenance
    Structured design references from 1,000+ curated websites for AI-powered web design. Retrieve real CSS values, typography specs, color palettes, and design rationale via MCP.
    1
    MIT

  • Mobbin MCP Server

    pdcolandrea
    A
    license
    Not graded
    quality
    F
    maintenance
    Enables users to search and browse Mobbin's extensive library of mobile app designs, screenshots, and user flows directly from Claude. It allows for detailed exploration of UI patterns, elements, and personal collections using reverse-engineered API access.
    140 npm
    46
    ISC

  • ui-ux-pro-mcp

    redf0x1
    A
    license
    A
    quality
    D
    maintenance
    🎨 AI-powered UI/UX design intelligence - 1519+ curated design resources through MCP | React, Vue, Next.js, Flutter & more
    7
    310 npm
    36
    MIT

  • A1 Gallery MCP Server

    bryntay
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides curated real website design references with structured JSON data on type, spacing, palette, and layout. Enables AI agents to search, browse, and analyze over 1,000 sites and their sections.
    1
    MIT
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources