# Refcat (remote · mcp.refcat.app)

Search 1M real UI flows and 3.3M screens from shipped apps, sites, emails and games.

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.refcat.app`: 78/100 (this document), [markdown](https://verifymcp.io/servers/app-refcat-refcat/mcp.md), [page](https://verifymcp.io/servers/app-refcat-refcat/mcp)

## Channel facts

- Endpoint: `https://mcp.refcat.app/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1711 tokens (~95/item across 18 items; 18 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 30% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Refcat MCP server?

Refcat is a hosted endpoint at https://mcp.refcat.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http app-refcat-refcat 'https://mcp.refcat.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-refcat-refcat": {
      "url": "https://mcp.refcat.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-refcat-refcat": {
      "type": "http",
      "url": "https://mcp.refcat.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-refcat-refcat]
url = "https://mcp.refcat.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-refcat-refcat": {
      "type": "remote",
      "url": "https://mcp.refcat.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-refcat-refcat --url 'https://mcp.refcat.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-refcat-refcat:
    url: "https://mcp.refcat.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-refcat-refcat": {
      "Transport": "http",
      "Url": "https://mcp.refcat.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-refcat-refcat -t streamable-http -u 'https://mcp.refcat.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-refcat-refcat": {
      "type": "http",
      "url": "https://mcp.refcat.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 76, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-01 (score 76)

First indexed and scored.

## MCP tools (18)

### `list_facets` (~82 tokens)

List filter values

The filter vocabulary with real counts (number of flows): platform, flowIntents, uiComponents, pageType and screenPatterns. Call this before filtering search_screens or search_flows so filters are real values, not guesses. Optional query/filters narrow every count, flowIntents included.

Input parameters:

- `filters` (object)
- `query` (string)

### `get_screen` (~156 tokens)

Get screen

One catalog screen with its image and structure. Returns an image block (look at it for color, typography and spacing) and JSON with app, flow, platform, pageType, screenPatterns, uiComponents, keyTexts, dimensions, capturedAt and `elements` (OCR text and hotspots with normalized bbox [x0,y0,x1,y1], sorted top to bottom: use them to reproduce hierarchy, order and positions). image 'small' is ~800px wide (~1-2k tokens), 'full' 1800px. Cite the app, flow and capture date when you build from it.

Input parameters:

- `image` (string)
- `includeElements` (boolean)
- `screenDocId` (string, required)

### `search_screens_by_image` (~72 tokens)

Search screens by image

Find catalog screens that look like your images (base64, e.g. a screenshot of the app you are building). Then call get_screen on the matches to compare. Free plans: up to 2 images and 12 results.

Input parameters:

- `images` (array, required)
- `limit` (integer)

### `search_screens` (~126 tokens)

Search screens

Search individual UI screens by description, app name or site ('paywall with annual plan first', 'Spotify', 'linear.app'). Returns metadata per screen; set includeImages to also get the top screens as images (max 4, ~1-2k tokens each). Call get_screen for the full structure of one.

Input parameters:

- `filters` (object)
- `includeImages` (boolean)
- `limit` (integer)
- `offset` (integer): Skip this many results (pagination)
- `query` (string, required): Free text, an app name, or a website

### `search_flows` (~135 tokens)

Search flows

Search whole flows (ordered screen sequences) by intent, app or description. Then get_flow for the steps.

Input parameters:

- `flowIntents` (array)
- `limit` (integer)
- `offset` (integer): Skip this many results (pagination)
- `platform` (array): ios, android, web (desktop sites), email (brand email galleries), game (game UI: menus, HUD, inventory), reference (curated design references like bento grids), store (app store listing carousels) or…
- `query` (string)

### `search_emails` (~123 tokens)

Search emails

Search real product emails (welcome, receipts, onboarding, re-engagement…) by description or brand. Each result is one email with its desktop and/or mobile image; when hasHtml is true, get_email_html returns the original HTML to adapt. Needs Pro.

Input parameters:

- `appId` (array): Limit to these brands
- `flowIntents` (array)
- `limit` (integer)
- `offset` (integer): Skip this many results (pagination)
- `query` (string): Free text, e.g. 'welcome email with a big hero image'

### `get_email_html` (~66 tokens)

Get email HTML

The original HTML of one email from search_emails (tables, font fallbacks, dark mode included). Adapt it to the user's brand instead of writing email HTML from scratch. Pro, or this week's free flows.

Input parameters:

- `emailId` (string, required): emailId from search_emails

### `search_apps` (~113 tokens)

Search apps

Find apps in the catalog by name, website or theme ('nubank', 'linear.app', 'meditation').

Input parameters:

- `limit` (integer)
- `platform` (array): ios, android, web (desktop sites), email (brand email galleries), game (game UI: menus, HUD, inventory), reference (curated design references like bento grids), store (app store listing carousels) or…
- `query` (string, required)

### `get_app` (~44 tokens)

Get app

Metadata for one app in the catalog. Accepts an appId or a slug like 'spotify'. get_app_flows lists its flows.

Input parameters:

- `appId` (string, required)

### `get_app_flows` (~86 tokens)

Get app flows

The flows of one app (onboarding, checkout, settings…) in order, with capture date. Accepts an appId or slug. Big apps have hundreds of flows: page with offset. Then get_flow for the steps of one.

Input parameters:

- `appId` (string, required)
- `limit` (integer)
- `offset` (integer): Skip this many results (pagination)

### `similar_apps` (~38 tokens)

Find similar apps

Apps like this one, ranked from the app's own flow themes. Accepts an appId or slug.

Input parameters:

- `appId` (string, required)

### `get_flow` (~88 tokens)

Get flow

One flow with every step in order. Compact by default: each step has screenDocId (for get_screen), pageType, patterns, components and keyTexts. include 'elements' adds OCR/hotspot boxes per step (large: tens of thousands of tokens for a long flow); 'connections' adds step links.

Input parameters:

- `flowId` (string, required)
- `include` (array)

### `get_flow_history` (~44 tokens)

Get flow history

Earlier captures of the same flow (how it changed over time): capture date, screen count and up to 3 preview images each.

Input parameters:

- `flowId` (string, required)

### `similar_screens` (~62 tokens)

Find similar screens

Screens that look like a given screen. Visual, not keyword — no quota. includeImages returns the top matches as images (max 4).

Input parameters:

- `includeImages` (boolean)
- `limit` (integer)
- `screenDocId` (string, required)

### `list_categories` (~106 tokens)

List categories

The catalog's category rail for a platform, with the key list_apps filters by. Emails, games, store listings and ads have their own rails.

Input parameters:

- `platform` (string): ios, android, web (desktop sites), email (brand email galleries), game (game UI: menus, HUD, inventory), reference (curated design references like bento grids), store (app store listing carousels) or…

### `list_apps` (~131 tokens)

List apps

Apps in the catalog, optionally filtered by category key (from list_categories) or platform. Platform `email` lists brands with email galleries.

Input parameters:

- `category` (string)
- `limit` (integer)
- `offset` (integer): Skip this many results (pagination)
- `platform` (string): ios, android, web (desktop sites), email (brand email galleries), game (game UI: menus, HUD, inventory), reference (curated design references like bento grids), store (app store listing carousels) or…

### `list_projects` (~16 tokens)

List projects

The caller's projects, newest first.

### `get_project` (~26 tokens)

Get project

One project with its screens, positions and connections.

Input parameters:

- `projectId` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-refcat-refcat/mcp#diagnostics

## Score history

- 2026-11-05: 78
- 2026-11-04: 77
- 2026-11-03: 77
- 2026-11-02: 76
- 2026-11-01: 76

## Common questions

### What is the Refcat MCP server?

Refcat is an MCP server listed in the public MCP registry as app.refcat/refcat. Search 1M real UI flows and 3.3M screens from shipped apps, sites, emails and games. This page covers its hosted endpoint (https://mcp.refcat.app/mcp).

### Is the Refcat MCP server safe to use?

Refcat scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Refcat MCP server expose?

Refcat exposes 18 tools: list_facets, get_screen, search_screens_by_image, search_screens, search_flows, and 13 more. Their descriptions and schemas cost roughly 1,514 tokens of context every time the server is loaded.

### Does the Refcat MCP server require authentication?

Yes. Refcat asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Refcat MCP server still maintained?

Refcat is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.refcat.app/mcp
- Authorisation metadata: https://mcp.refcat.app/.well-known/oauth-protected-resource/mcp
- Website: https://refcat.app/en/guides/mcp
- Changelog RSS feed: https://verifymcp.io/servers/app-refcat-refcat/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-refcat-refcat/mcp.json
- HTML version of this page: https://verifymcp.io/servers/app-refcat-refcat/mcp