# Boxlist (remote · mcp.boxlist.com)

Taste-based film, TV, book and game picks: similar in feel, taste reads, picks for two.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.boxlist.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-boxlist-mcp-boxlist/mcp.md), [page](https://verifymcp.io/servers/com-boxlist-mcp-boxlist/mcp)

## Channel facts

- Endpoint: `https://mcp.boxlist.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## 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 2026-11-21.

- **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. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1246 tokens (~249/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 89% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

Boxlist is a hosted endpoint at https://mcp.boxlist.com/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 com-boxlist-mcp-boxlist 'https://mcp.boxlist.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-boxlist-mcp-boxlist": {
      "url": "https://mcp.boxlist.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-boxlist-mcp-boxlist]
url = "https://mcp.boxlist.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-boxlist-mcp-boxlist --url 'https://mcp.boxlist.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-boxlist-mcp-boxlist:
    url: "https://mcp.boxlist.com/mcp"
```

### Netclaw

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

### Vellum

```bash
assistant mcp add com-boxlist-mcp-boxlist -t streamable-http -u 'https://mcp.boxlist.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-boxlist-mcp-boxlist": {
      "type": "http",
      "url": "https://mcp.boxlist.com/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.

### 2026-11-21 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 72, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-11 (score 71)

First indexed and scored.

## MCP tools (5)

### `search_titles` (~157 tokens)

Search Boxlist titles

Find films, TV series, books and video games in the Boxlist catalogue by name (books also by author). Returns each title's boxlist.com page and a `ref` to pass to the other Boxlist tools. Use it to pin down the right title (e.g. which "Dune") before asking for a taste profile or similar titles.

Input parameters:

- `limit` (integer): How many results (1-5, default 5).
- `media` (array): Restrict to these media: "film", "tv", "book", "game". Omit for all four.
- `query` (string, required): Title or part of it, optionally with a year ("Dune 2021"). Books also match by author.

Output parameters:

- `attribution` (object): Required credit: show "Data from Boxlist" with the link wherever these results are used.
- `nextStep`
- `note` (string)
- `query` (string)
- `results` (array)

### `get_title_taste_profile` (~192 tokens)

Title taste profile

How a film, TV series, book or video game feels, in plain words: its scores on Boxlist's ten taste dimensions (pace, originality, wholesomeness, weightiness, realism, intricacy, linearity, style, scale, emotional punch), its story themes and the Taste Type it suits. For films and TV it adds where to watch in the UK and US; for games, platforms and stores. Use it to explain why someone might or might not enjoy a title.

Input parameters:

- `media` (string): Which medium you mean, when the name is shared (e.g. "book" for Dune the novel).
- `title` (string, required): A title name ("Succession", "Dune (2021)"), a boxlist.com URL, or a `ref` from another Boxlist tool.
- `year` (integer): Release year, to tell remakes apart.

Output parameters:

- `attribution` (object): Required credit: show "Data from Boxlist" with the link wherever these results are used.
- `dataFreshness` (string)
- `didYouMean` (array)
- `dimensions` (array)
- `genres` (array)
- `matchedBy` (string)
- `nextStep`
- `storyThemes` (array)
- `subjects` (array)
- `summary` (string): One or two plain sentences on how the title feels.
- `tasteType`: Which of the four Boxlist Taste Types this title most suits.
- `title` (object)
- `whereToPlay`: Games only.
- `whereToWatch`: Films and TV only: UK and US services.

### `find_similar_in_feel` (~210 tokens)

Similar in feel

Titles that feel like a given film, TV series, book or game — matched on Boxlist's taste dimensions, story themes and subjects, not just genre or cast — across all four media or only the ones you choose. Each result says what it shares with the starting title. Good for "I loved X, what next?" and cross-media asks like "a book that feels like Succession".

Input parameters:

- `limit` (integer): How many titles (1-5, default 5).
- `media` (array): Media to suggest from. Omit for all four (films, TV, books, games). Use ["book"] for "what should I read next".
- `title` (string, required): The title to start from: a name, a boxlist.com URL, or a `ref` from another Boxlist tool.
- `titleMedia` (string): Medium of the starting title, when the name is shared (e.g. "book" for Dune the novel).

Output parameters:

- `attribution` (object): Required credit: show "Data from Boxlist" with the link wherever these results are used.
- `didYouMean` (array)
- `matchedBy` (string)
- `method` (string): "site" = the exact "Similar in feel" list shown on boxlist.com; "model" = the same model run live (cross-media).
- `nextStep`
- `note` (string): Present when Boxlist has little story data for the starting title, so matches are looser.
- `results` (array)
- `seed` (object)

### `quick_taste_read` (~211 tokens)

Quick taste read

Turn 2 to 5 titles someone loves (films, TV, books or games, mixed is fine) into a short Taste Fingerprint™ reading — their leans on Boxlist's taste dimensions, their Taste Type and recurring themes — plus suggestions with a Boxlist match band and a reason for each. Anonymous: no account, nothing stored. Use it for "what should I watch/read/play, I like X, Y and Z".

Input parameters:

- `limit` (integer): How many suggestions (1-5, default 5).
- `lovedTitles` (array, required): 2 to 5 films, shows, books or games the person loves (3 or more give a better read): names ("Succession", "Dune (2021)"), boxlist.com URLs or refs.
- `media` (array): Same as suggestFrom (either name works).
- `suggestFrom` (array): Media to suggest from. Omit for all four (leaning towards the medium of the loved titles).

Output parameters:

- `attribution` (object): Required credit: show "Data from Boxlist" with the link wherever these results are used.
- `nextStep`
- `privacy` (string)
- `suggestions` (array)
- `tasteFingerprint` (object)
- `understood` (array)

### `match_for_two` (~176 tokens)

Match for two

Find titles two people will both enjoy, from one to five titles each of them loves. Blends their two Taste Fingerprint™ profiles the way Boxlist's Watch together does, skips anything either is likely to dislike, and returns picks with a band for the pair and for each person, plus where their tastes agree and differ. Defaults to films and TV; books and games can be added. Anonymous, nothing stored.

Input parameters:

- `limit` (integer): How many picks (1-5, default 5).
- `media` (array): Same as suggestFrom (either name works).
- `personA` (object, required)
- `personB` (object, required)
- `suggestFrom` (array): Media to pick from. Omit for films and TV (watching together); add "book" or "game" if wanted.

Output parameters:

- `attribution` (object): Required credit: show "Data from Boxlist" with the link wherever these results are used.
- `commonGround` (string): Where the two tastes agree and where they pull apart.
- `nextStep`
- `personA` (object)
- `personB` (object)
- `picks` (array)
- `privacy` (string)

## Diagnostics

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

## Score history

- 2026-11-21: 76
- 2026-11-20: 75
- 2026-11-19: 75
- 2026-11-18: 74
- 2026-11-17: 74
- 2026-11-16: 73
- 2026-11-15: 73
- 2026-11-14: 73
- 2026-11-13: 72
- 2026-11-12: 72
- 2026-11-11: 71

## Common questions

### What is the Boxlist MCP server?

Boxlist is an MCP server listed in the public MCP registry as com.boxlist.mcp/boxlist. Taste-based film, TV, book and game picks: similar in feel, taste reads, picks for two. This page covers its hosted endpoint (https://mcp.boxlist.com/mcp).

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

Boxlist scores 76 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 Boxlist MCP server expose?

Boxlist exposes 5 tools: search_titles, get_title_taste_profile, find_similar_in_feel, quick_taste_read, match_for_two. Their descriptions and schemas cost roughly 946 tokens of context every time the server is loaded.

### Does the Boxlist MCP server require authentication?

No. We connected to Boxlist without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Boxlist MCP server still maintained?

Boxlist is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Boxlist MCP server?

VerifyMCP ran 13 checks on Boxlist, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.boxlist.com/mcp
- Website: https://www.boxlist.com/ai-assistants
- Changelog RSS feed: https://verifymcp.io/servers/com-boxlist-mcp-boxlist/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-boxlist-mcp-boxlist/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-boxlist-mcp-boxlist/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-boxlist-mcp-boxlist/mcp
