# io.github.Nutlope/inspo (remote · inspomcp.dev)

Real production websites for coding agents: palettes, fonts, fold autopsies and reference JSX.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-02

## Components

- remote · `inspomcp.dev`: 80/100 (this document), [markdown](https://verifymcp.io/servers/nutlope-inspo/api-mcp.md), [page](https://verifymcp.io/servers/nutlope-inspo/api-mcp)
- npm · `inspo-mcp`: 39/100, [markdown](https://verifymcp.io/servers/nutlope-inspo/inspo-mcp.md), [page](https://verifymcp.io/servers/nutlope-inspo/inspo-mcp)

## Channel facts

- Endpoint: `https://inspomcp.dev/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.16`

## 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 2026-10-02.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2938 tokens (~195/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% 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 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 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 io.github.Nutlope/inspo MCP server?

io.github.Nutlope/inspo is a hosted endpoint at https://inspomcp.dev/api/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 nutlope-inspo 'https://inspomcp.dev/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "nutlope-inspo": {
      "url": "https://inspomcp.dev/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "nutlope-inspo": {
      "type": "http",
      "url": "https://inspomcp.dev/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.nutlope-inspo]
url = "https://inspomcp.dev/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nutlope-inspo": {
      "type": "remote",
      "url": "https://inspomcp.dev/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nutlope-inspo --url 'https://inspomcp.dev/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  nutlope-inspo:
    url: "https://inspomcp.dev/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "nutlope-inspo": {
      "Transport": "http",
      "Url": "https://inspomcp.dev/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add nutlope-inspo -t streamable-http -u 'https://inspomcp.dev/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "nutlope-inspo": {
      "type": "http",
      "url": "https://inspomcp.dev/api/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.

### 2026-10-02 (score 80, 0)

- [functional] Server version: hosted-5d2f4ea → hosted-0e1e636

### 2026-10-01 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-29 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 78, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-26 (score 77, 0)

- [functional] Server version: hosted-85acb10 → hosted-5d2f4ea

### 2026-09-25 (score 77, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (15)

### `search_screens` (~535 tokens)

Search the archive of real website screenshots. Returns screens with palette, fonts, components and image URLs.

Input parameters:

- `accentHue` (string): Accent temperature: 'warm' (10-60°), 'cool' (200-300°), 'neutral' (unsaturated), 'chromatic-other' (greens, magentas, everything else).
- `color` (string): Color word - 'warm', 'cool', 'monochrome', 'neon', 'earthy'
- `detail` (string): 'standard' (default): northstar, palette, fonts, axes, macro and tags per row, plus the fold-by-fold autopsy on the top 3. 'full': the autopsy on every row (~300 tokens each; only if you will read th…
- `device` (string): 'mobile' restricts to sites with a 375px capture pair and inlines the mobile thumbnail. Default: desktop.
- `displayClass` (string): Construction of the display face: 'grotesk-sans', 'geometric-sans', 'roman-serif', 'mono', 'display-condensed-bold', etc.
- `industry` (string): Filter to one industry (e.g. 'saas', 'fintech', 'portfolio')
- `limit` (integer)
- `macrostructure` (string): Filter to a macrostructure (e.g. 'bento-grid')
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `mode` (string): light or dark
- `pageType` (string): Filter to a page kind: 'landing' (default homepages), 'pricing', 'features', 'auth', 'about', 'blog', 'changelog', 'docs', 'other'
- `paperBand` (string): Surface lightness, measured from the capture: 'dark' (<30% L), 'mid' (30-85%), 'light' (>85%). More reliable than `mode`, which is tagged and disagrees with the measurement on ~15% of rows.
- `query` (string): Natural-language description of what you're looking for. e.g. 'minimalist editorial agency portfolio'
- `style` (string): Filter to one visual style (e.g. 'minimalism', 'editorial')
- `vibe` (string): Mood / vibe - 'calm', 'loud', 'luxe', 'technical', 'soft', etc.

### `get_screen` (~49 tokens)

Fetch the full record for one screen by slug - every viewport variant, palette, fonts, tech stack, designer credit.

Input parameters:

- `slug` (string, required): Screen slug, e.g. 'atelier-mira'

### `get_design_system` (~118 tokens)

The full DESIGN.md for one screen - real fonts, frequency-ranked palette, CSS variables, detected tech, colour roles, type ramp. Thin captured tokens are supplemented by a live fetch of the source; `live=false` skips that.

Input parameters:

- `live` (boolean): If true (default), supplement thin captured tokens by fetching the source URL via study(). Set false to skip the network round-trip.
- `slug` (string, required): Screen slug, e.g. 'linear-app'. Use search_screens or find_similar first to discover slugs.

### `find_similar` (~188 tokens)

A screen's nearest design neighbours - ranked by design-similarity embeddings where available, else by macrostructure / industry / style overlap. One result per site.

Input parameters:

- `detail` (string): 'standard' (default): northstar, palette, fonts, axes, macro and tags per row, plus the fold-by-fold autopsy on the top 3. 'full': the autopsy on every row (~300 tokens each; only if you will read th…
- `limit` (integer)
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `sameSite` (boolean): Include other pages of the same site (default false: neighbours are other sites).
- `slug` (string, required)

### `compare` (~101 tokens)

Compare 2-4 captured sites across palette, typefaces, macrostructure, mode, style tags, type/spacing/radius scales and container width. Returns per-site breakdowns plus what they share - triangulates a house style from a few references.

Input parameters:

- `slugs` (array, required): 2-4 screen slugs to compare, e.g. ['linear-app','stripe-com','vercel-com']. Discover slugs with search_screens / find_similar.

### `find_by_color` (~257 tokens)

Real sites whose extracted palette sits near a hex colour (OKLAB distance, so 'close' means the same colour family, not just the same hue). Use when a brief names a brand colour.

Input parameters:

- `detail` (string): 'standard' (default): northstar, palette, fonts, axes, macro and tags per row, plus the fold-by-fold autopsy on the top 3. 'full': the autopsy on every row (~300 tokens each; only if you will read th…
- `hex` (string, required): Target colour as a hex string ('#c7402f', 'c7402f', '#fff'). Case-insensitive. 3- or 6-digit.
- `limit` (integer)
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `tolerance` (number): Max OKLAB distance to count as a match. Defaults to 0.15 ('same family'). 0.05 ≈ 'near-identical', 0.30 ≈ 'in the same hue zip code'.

### `find_examples_for_macrostructure` (~231 tokens)

Real sites exemplifying one of the 19 named macrostructures. Call it at the macrostructure-pick step. Accepts slugs ('bento-grid') or display names ('Bento Grid').

Input parameters:

- `detail` (string): 'standard' (default): northstar, palette, fonts, axes, macro and tags per row, plus the fold-by-fold autopsy on the top 3. 'full': the autopsy on every row (~300 tokens each; only if you will read th…
- `device` (string): 'mobile' restricts to sites with a 375px capture pair and inlines the mobile thumbnail. Default: desktop.
- `limit` (integer)
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `name` (string, required): Macrostructure name. e.g. 'bento-grid', 'Bento Grid', 'specimen', 'Marquee Hero'.

### `list_collections` (~37 tokens)

List every editor-curated issue. Use this for thematic browsing - e.g. all 'Editorial Layouts' or 'Dark Product Pages'.

### `get_filters` (~49 tokens)

Every value the filters accept: styles, industries, macrostructures, modes, vibes, colors, page types, component types. Zero input. Call it when unsure - an out-of-vocabulary value errors.

### `get_site_pages` (~141 tokens)

A site's captured pages as an ordered flow (landing → pricing → features → ...) with titles, northstars and thumbnails - how a real product sequences its pages. No arguments returns the directory of flow-capable sites. Accepts a site or screen slug.

Input parameters:

- `limit` (integer): Directory mode only: max sites to list.
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `siteSlug` (string): Site slug (e.g. 'linear-app') or any screen slug from that site. Omit to list flow-capable sites instead.

### `find_components` (~238 tokens)

Real sites featuring a specific UI component (hero, pricing, features, cta, nav, footer, testimonial, logo-cloud, faq, stat), with a per-element crop where one exists. For copy-pasteable code use get_reference_jsx.

Input parameters:

- `color` (string): Color word - 'warm', 'cool', 'monochrome', etc.
- `device` (string): 'mobile' restricts to sites with a 375px capture pair and inlines the mobile thumbnail. Default: desktop.
- `industry` (string)
- `limit` (integer)
- `macrostructure` (string)
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `mode` (string)
- `pageType` (string): Only components from this page kind (e.g. 'pricing')
- `style` (string): Filter the parent site's style
- `type` (string, required): Which component type to find
- `vibe` (string): Mood - 'calm', 'loud', 'luxe', etc.

### `get_collection` (~153 tokens)

Fetch one issue by slug, including the editor's blurb and ordered screen list.

Input parameters:

- `detail` (string): 'standard' (default): northstar, palette, fonts, axes, macro and tags per row, plus the fold-by-fold autopsy on the top 3. 'full': the autopsy on every row (~300 tokens each; only if you will read th…
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `slug` (string, required): Collection slug, e.g. 'editorial-layouts'

### `find_reference_components` (~111 tokens)

The canonical reference components as an index: id, label, macrostructure and a note for each hero / pricing / cta / nav / footer archetype. Pick one, then get_reference_jsx(type, id) for its source.

Input parameters:

- `macro` (string): Substring match on the component's macro field - e.g. 'Marquee' matches 'Marquee Hero'.
- `type` (string): Component category (hero, pricing, cta, …). Omit to scan all types.

### `recommend` (~331 tokens)

Orchestrator - start here for a brief. One call returns a macrostructure pick, 5 real exemplars, matching reference components (source via get_reference_jsx), a palette suggestion, and an `evidence` packet measuring the genre's paper band / display class / accent hue. Pass a macrostructure to skip the pick step. No LLM call.

Input parameters:

- `brief` (string, required): The user's design brief in plain English. E.g. 'calm meditation app', 'dark dev-tool that helps teams ship faster'.
- `color` (string): Optional colour word.
- `detail` (string): 'standard' (default): northstar, palette, fonts, axes, macro and tags per row, plus the fold-by-fold autopsy on the top 3. 'full': the autopsy on every row (~300 tokens each; only if you will read th…
- `device` (string): 'mobile' restricts to sites with a 375px capture pair and inlines the mobile thumbnail. Default: desktop.
- `macrostructure` (string): Optional: a macrostructure already picked. Skips the pick step.
- `maxTokens` (integer): Approximate token ceiling for this response. Trims lower-ranked results and thumbnails; the top result and all URLs survive.
- `mode` (string): Optional: 'light' or 'dark'.
- `pageType` (string): Optional: 'landing', 'pricing', 'features', etc.
- `vibe` (string): Optional vibe filter.

### `get_reference_jsx` (~77 tokens)

The full canonical JSX source for one reference component, including the header stamp naming its macrostructure / theme / states. Copy-pasteable; tweak tokens to the target brand.

Input parameters:

- `id` (string, required): Reference id within that type (e.g. 'marquee', 'three-card').
- `type` (string, required): Component category

## Diagnostics

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

## Score history

- 2026-10-02: 80
- 2026-10-01: 80
- 2026-09-30: 79
- 2026-09-29: 79
- 2026-09-28: 78
- 2026-09-27: 78
- 2026-09-26: 77
- 2026-09-25: 77
- 2026-09-24: 76
- 2026-09-23: 76
- 2026-09-22: 75
- 2026-09-21: 75
- 2026-09-20: 74
- 2026-09-19: 74
- 2026-09-18: 73
- 2026-09-17: 73
- 2026-09-16: 73
- 2026-09-15: 72
- 2026-09-14: 72

## Common questions

### What is the io.github.Nutlope/inspo MCP server?

io.github.Nutlope/inspo is an MCP server listed in the public MCP registry as io.github.Nutlope/inspo. Real production websites for coding agents: palettes, fonts, fold autopsies and reference JSX. This page covers its hosted endpoint (https://inspomcp.dev/api/mcp).

### Is the io.github.Nutlope/inspo MCP server safe to use?

io.github.Nutlope/inspo scores 80 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 io.github.Nutlope/inspo MCP server expose?

io.github.Nutlope/inspo exposes 15 tools: search_screens, get_screen, get_design_system, find_similar, compare, and 10 more. Their descriptions and schemas cost roughly 2,616 tokens of context every time the server is loaded.

### Does the io.github.Nutlope/inspo MCP server require authentication?

No. We connected to io.github.Nutlope/inspo without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.Nutlope/inspo MCP server still maintained?

io.github.Nutlope/inspo is still listed as active in the MCP registry. We last reached this channel on 2 October 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://inspomcp.dev/api/mcp
- Repository: https://github.com/Nutlope/inspo
- Changelog RSS feed: https://verifymcp.io/servers/nutlope-inspo/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/nutlope-inspo/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/nutlope-inspo/api-mcp