Flownato Mcp

com.flownatov1.0.0Updated Oct 1, 2026

Mobile UI/UX design research: real app screens, user flows and UI patterns with cited evidence.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingMedia & DesignKnowledge & Memory

Overview

AI-generated overview

Lets an assistant search and compare real mobile app screens, user flows and UI patterns, with cited screen evidence.

What it does
A remote, read-only MCP server for mobile UI/UX design research. It exposes eleven tools, including search_ui_library and search_ui_screens for finding journeys and screens, analyze_ui_pattern and explore_ui_patterns for measuring or discovering recurring patterns, compare_ui_flows for comparing the same product moment across two or three apps, inspect_app_library and inspect_library_coverage for coverage summaries, check_ui_presence for scoped yes/no checks, inspect_ui_resources for release-bound follow-up retrieval, and get_screen_image for returning a published screen image. Results cite the journey and step identifiers they were built from, and pattern counts are descriptive rather…
When to use it
Useful when a designer or developer wants evidence about how real mobile apps handle a specific interface moment instead of guessing, for example checkout steps, phone-number entry, onboarding journeys or bottom-sheet usage. It suits research and comparison questions about published app screens and flows.
Requirements
A remote Streamable HTTP endpoint at Authentication is OAuth 2.1 authorization code with PKCE through a browser sign-in and read-only consent screen; no API keys are pasted. A Flownato account is required, and free accounts see only journeys marked free plus the first 3 screens of other journeys. Both tiers are metered at a default safety limit of 500 tool calls per UTC day.
Before you install
Access is tiered: free accounts get locked results for most screens, and get_screen_image answers PREMIUM_REQUIRED for a locked screen. Sign-in grants read-only access to your Flownato account, and tokens refresh until the grant is revoked. The server is read-only and does not store prompts, arguments or results; screenshot URLs are signed and short lived. The server itself is not open source.

Installation

In SourceWeft

  1. Open Flownato Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "flownato-mcp": {
      "type": "http",
      "url": "https://agent.flownato.com/mcp"
    }
  }
}

README

Flownato MCP

[MCP Badge]

A remote, read-only Model Context Protocol server for mobile UI/UX design research. Built for product designers and developers, it gives MCP-compatible assistants (Claude, Cursor, Codex, Windsurf and others) access to Flownato's library of real mobile app screens, user flows and UI patterns, with every answer tied to published screen evidence.

  • Endpoint: https://agent.flownato.com/mcp (Streamable HTTP)
  • Auth: OAuth 2.1 authorization code with PKCE. Your browser opens Flownato sign-in and a read-only consent screen. No API keys to paste.
  • Access: every signed-in Flownato account can use every tool. Free accounts get the same access as on the website: complete journeys that flownato.com marks free, plus the first 3 screens of every other journey. Premium opens every screen.
  • Website: https://www.flownato.com/mcp

What it does

Flownato records real mobile apps such as Swiggy, Zepto, BookMyShow, redBus and Nykaa, then publishes reviewed screens, complete journeys and a UI pattern taxonomy. The MCP server lets an assistant search and compare that evidence instead of guessing what an interface looks like.

Typical questions it can answer with citations:

  • "How do grocery apps handle the delivery slot step in checkout?"
  • "Show me phone-number entry screens across booking apps."
  • "Compare the onboarding journey in Cricbuzz and FanCode."
  • "Which apps use a bottom sheet for store selection?"

Tools

ToolPurpose
whoamiReports the authenticated membership, what that tier can see, and the client.
search_ui_libraryFinds concrete journey examples for a research question.
search_ui_screensScreen-level search with exact interface text matching.
analyze_ui_patternMeasures one screen pattern, UI element, flow pattern or flow action across an optional app or category scope.
explore_ui_patternsDiscovers recurring patterns when you do not yet know which one to analyze.
compare_ui_flowsCompares the same product moment across two or three named apps.
inspect_app_librarySummarizes one app's published coverage, patterns, elements and journeys.
check_ui_presenceScoped yes/no presence checks with evidence.
inspect_library_coveragePaginated inventory of what is published.
inspect_ui_resourcesExact release-bound follow-up retrieval for returned resourceRef objects.
get_screen_imageReturns a published screen image inline after another tool supplies its asset ID.

All tools are read-only. Results cite the exact journey and step identifiers they were built from, and pattern counts are descriptive, never presented as best practice.

Connect

Claude Code plugin

The plugin installs the MCP server together with the flownato-ui-research skill, which tells the assistant when to look up real app flows and how to cite them:

text
/plugin marketplace add flownato/flownato-mcp/plugin install flownato@flownato

The same repository carries plugin manifests for Cursor (.cursor-plugin/) and Codex (.codex-plugin/). The skill lives in skills/flownato-ui-research/SKILL.md.

MCP server only

In clients that accept a remote mcpServers configuration, use:

json
{  "mcpServers": {    "flownato": {      "type": "http",      "url": "https://agent.flownato.com/mcp"    }  }}

Claude Code:

bash
claude mcp add --transport http flownato https://agent.flownato.com/mcp

On first use the client opens https://api.flownato.com/oauth/authorize in your browser. Sign in with your Flownato account and approve read-only access. Tokens are short lived and refresh silently until you revoke the grant.

Discovery documents:

  • Protected resource metadata: https://agent.flownato.com/.well-known/oauth-protected-resource/mcp
  • Authorization server metadata: https://api.flownato.com/.well-known/oauth-authorization-server

Access and limits

PlanWhat the MCP returns
Not signed inThe endpoint answers 401 with OAuth discovery metadata, so your client opens Flownato sign-in. Creating an account is free.
Free accountAll eleven tools. Journeys marked free on flownato.com (up to three per app) return every screen. Other journeys return their first 3 screens; the rest come back with locked: true, no asset ID and no image URL. Every result carries an access block with the locked counts and an upgrade link, and get_screen_image answers PREMIUM_REQUIRED for a locked screen.
PremiumAll eleven tools with the complete library.

Both tiers are metered at a default safety limit of 500 tool calls per UTC day.

Prompts, arguments and results are not stored. Screenshot URLs are signed and short lived, and the image endpoint rechecks membership when the image is fetched.

Privacy and scope

The server reads only the published product catalog: reviewed, immutable releases with privacy redaction applied. It has no access to raw crawl data, model output or other users' accounts. It answers UI and product-design research questions and declines unrelated requests.

Source

This repository documents the hosted service and holds its plugin manifests and skill. The server itself is part of Flownato's private product codebase (Python, FastAPI) and is not open source.

Marketplace metadata

lhm.plugin.json declares the existing LobeHub listing's category, remote endpoint, and all eleven MCP tool schemas. Its category is developer (displayed as Developer Skills on LobeHub), reflecting its use for UI/UX design and product development.

The endpoint requires OAuth before protocol initialization and tool discovery. An unauthenticated request returning 401 is expected; use the protected-resource metadata above to start sign-in. Directory crawlers cannot discover the tool list from an unauthenticated connection alone.

The server currently exposes tools, with no MCP prompt templates or MCP resources. Returned resourceRef objects are arguments to inspect_ui_resources; they are not entries in the MCP resources/list capability. Keep marketplace declarations consistent with the server's actual capabilities.

The public badge above supports LobeHub's README claim-status check. Prefer this public verification route when available. Updating this public listing does not justify granting a directory read/write access to private GitHub repositories.

Already verified maintainers can update the existing listing with the official @lobehub/market-cli (Node.js 22 or newer):

bash
# Sign in to LobeHub, then check existing GitHub verification:npx -y @lobehub/market-cli loginnpx -y @lobehub/market-cli github status
# Requires ownership verification; run after reviewing lhm.plugin.json:npx -y @lobehub/market-cli plugin update --dir "$PWD"

Review requested permissions before connecting any GitHub account. If a claim or update requires broad repo or workflow access, leave that connection disabled and request a narrower verification method from LobeHub.

When tool signatures change, refresh tools from the authenticated server's tools/list response before publishing. Keep prompts and resources empty unless the server implements them. The listing version remains 1.0.0 for this metadata correction; it does not represent a new server release. Verify the public listing after each update.

Links

Source: README.md at commit 0a36199

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 1, 2026