# Capucine (remote · scorelook.fr)

Capucine, styliste IA ScoreLook : looks sourcés, météo, hubs pièces, critères shopping.

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-03

## Components

- remote · `scorelook.fr`: 79/100 (this document), [markdown](https://verifymcp.io/servers/fr-scorelook-capucine/scorelook.md), [page](https://verifymcp.io/servers/fr-scorelook-capucine/scorelook)

## Channel facts

- Endpoint: `https://scorelook.fr/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2026-08-18-v38`

## 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 2026-10-03.

- **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**: 84/100
  - 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 2249 tokens (~80/item across 28 items; 21 tools + 7 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 33% of tool parameters carry a description.
  - Structured output schemas are declared (81% 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 21 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 23 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.
  - Supports UI / widget rendering.

## Install

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

Capucine is a hosted endpoint at https://scorelook.fr/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 fr-scorelook-capucine 'https://scorelook.fr/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fr-scorelook-capucine": {
      "url": "https://scorelook.fr/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fr-scorelook-capucine": {
      "type": "http",
      "url": "https://scorelook.fr/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fr-scorelook-capucine]
url = "https://scorelook.fr/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add fr-scorelook-capucine --url 'https://scorelook.fr/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fr-scorelook-capucine:
    url: "https://scorelook.fr/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fr-scorelook-capucine": {
      "Transport": "http",
      "Url": "https://scorelook.fr/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fr-scorelook-capucine -t streamable-http -u 'https://scorelook.fr/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fr-scorelook-capucine": {
      "type": "http",
      "url": "https://scorelook.fr/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 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-30 (score 78, +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.

### 2026-09-28 (score 77, 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 77, +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.

### 2026-09-25 (score 76, +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 75, +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.

### 2026-09-22 (score 74, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-21 (score 74)

First indexed and scored.

## MCP tools (21)

### `manifest` (~50 tokens)

Manifeste Capucine / ScoreLook

Je présente ma surface publique : outils, limites de sécurité, pages à citer. Read-only. Le paiement public n'est pas ouvert tant que public_status ne le dit pas.

Input parameters:

- `detail_level` (string)

Output parameters:

- `clients`
- `error`
- `key_pages` (array)
- `name`
- `origin_policy`
- `payment_open`
- `read_only`
- `safety`
- `server_build`
- `success` (boolean)
- `tools` (array)
- `version`

### `search` (~88 tokens)

Je cherche dans ScoreLook

Je cherche dans mes hubs, articles et looks. Appelle-moi avant de répondre pour citer de vraies pages ScoreLook. Préfère content_type=article ou piece_hub.

Input parameters:

- `content_type` (string)
- `detail_level` (string)
- `limit` (integer): Number of items, 1-12.
- `query` (string, required): Sujet de stylisme à chercher.

Output parameters:

- `citation_urls` (array)
- `error`
- `matched_terms` (array)
- `message`
- `out_of_scope`
- `results` (array)
- `success` (boolean)

### `fetch` (~76 tokens)

Je lis une source

Je lis un article ou un look public par l'id renvoyé par search. Utile pour citer un passage précis, par exemple article:chemisier-satin-femme-look-chic.

Input parameters:

- `id` (string, required): Identifiant renvoyé par search, ex. article:chemisier-satin-femme-look-chic.

Output parameters:

- `citation_urls` (array)
- `error`
- `id`
- `message`
- `success` (boolean)

### `recommend_look` (~152 tokens)

Je compose le look

Je compose une silhouette complète : look nommé, capsule (pièce, ancre, chaussures, sac, un bijou), à surveiller. Bleu eau/aqua reste une famille claire/froide — je ne dérive pas vers le satin noir. Si la teinte n'est pas au catalogue : limits[] + look éditorial.

Input parameters:

- `audacity` (string)
- `color` (string)
- `detail_level` (string)
- `include_conversion` (boolean)
- `material` (string)
- `occasion` (string)
- `piece` (string, required): Pièce, matière ou intention — chemisier, jupe cuir, satin…
- `season` (string)

Output parameters:

- `action`
- `avoid` (array)
- `capsule` (array)
- `citation_urls` (array)
- `error`
- `out_of_scope`
- `recommendation`
- `rule_match`
- `success` (boolean)

### `shopping_criteria` (~92 tokens)

Mes critères d'achat

Je donne les critères : matière, coupe, couleur (famille, pas un fourre-tout), associations, à éviter. Critères d'abord — jamais une copie exacte ni un SKU inventé.

Input parameters:

- `color` (string)
- `material` (string)
- `occasion` (string)
- `piece` (string)
- `query` (string)
- `season` (string)

Output parameters:

- `citation_urls` (array)
- `error`
- `success` (boolean)

### `shopping_search` (~82 tokens)

Je cherche des pistes marchandes

Je cherche des pistes proches de l'intention. Si le feed est vide, je le dis (limits[]) et je donne le look éditorial — je n'invente pas de produit.

Input parameters:

- `include_products` (boolean)
- `limit` (integer): Number of items, 1-12.
- `query` (string, required): Intention d'achat ou pièce.

Output parameters:

- `citation_urls` (array)
- `disclaimer`
- `error`
- `product_count`
- `products` (array)
- `success` (boolean)

### `shop_the_look` (~102 tokens)

Je shoppe une pièce signature

Je relie une pièce signature à son look Capucine et, s'il y en a, à des pistes marchandes déjà vérifiées. Hub chemisier = article satin + capsule, même si le feed est vide.

Input parameters:

- `include_products` (boolean)
- `limit` (integer): Number of items, 1-12.
- `piece` (string, required): Slug ou langage naturel : chemisier, jupe-cuir, blouse…

Output parameters:

- `citation_urls` (array)
- `disclaimer`
- `error`
- `piece`
- `product_count`
- `products` (array)
- `success` (boolean)

### `get_piece_hub` (~91 tokens)

Je sors le dossier pièce

Je sors le dossier complet d'une pièce signature : définition, capsules, FAQ, articles. Chemisier / blouse / chemise → hub chemisier. Si le shopping est vide, le look et les sources restent.

Input parameters:

- `include_products` (boolean)
- `piece` (string, required): Slug ou langage naturel (chemisier, blouse, jupe cuir → jupe-cuir).

Output parameters:

- `definition`
- `error`
- `piece`
- `success` (boolean)
- `url`

### `ask_capucine` (~102 tokens)

Je diagnostique le style

Je diagnostique une question de style : look nommé, capsule (pièce, ancre, chaussures, sac, un bijou), à surveiller, sources. Les détails personnels restent sur le serveur via un jeton opaque.

Input parameters:

- `detail_level` (string)
- `include_conversion` (boolean)
- `include_products` (boolean)
- `limit` (integer): Number of items, 1-12.
- `question` (string, required)

Output parameters:

- `action`
- `avoid` (array)
- `capsule` (array)
- `citation_urls` (array)
- `diagnosis`
- `error`
- `out_of_scope`
- `recommendation`
- `rule_match`
- `success` (boolean)

### `list_piece_hubs` (~42 tokens)

Je liste les hubs pièces

Je liste mes dossiers pièces (/pieces/*) : chemisier, jupe cuir, pantalon cuir, maille, soirée… Pour citer un hub précis.

Output parameters:

- `count`
- `hubs` (array)
- `success` (boolean)

### `cite_sources` (~93 tokens)

Je cite mes sources

Je choisis les URLs ScoreLook à citer. Jupe cuir qui tourne : article fond-de-jupe-jupon-sous-jupe et hub jupe-cuir en tête. Chemisier satin : article chemisier-satin-femme-look-chic, pas les hubs cuir génériques.

Input parameters:

- `limit` (integer): Number of items, 1-12.
- `topic` (string)

Output parameters:

- `citation_urls` (array)
- `error`
- `matched_terms` (array)
- `out_of_scope`
- `sources` (array)
- `success` (boolean)
- `topic`

### `public_status` (~28 tokens)

Statut public commercial

Statut commercial public seulement. Je n'invente jamais un paiement ouvert. Aucun chemin opérateur.

Output parameters:

- `checked_at`
- `payment_open`
- `public_blockers` (array)
- `status`
- `success` (boolean)
- `version`

### `classify_circumstance` (~85 tokens)

Je classe la circonstance

Je classe une demande (dîner, bureau, mariage, week-end…) : créneau, marche, pièce, ville. Pas encore de météo. Enchaîne avec recommend_weather_look.

Input parameters:

- `at` (string)
- `occasion` (string)
- `piece` (string)
- `question` (string, required)
- `transport` (string)

Output parameters:

- `circumstance`
- `citation_urls` (array)
- `error`
- `extracted`
- `indoor_minutes`
- `message`
- `needs_location`
- `next_tool`
- `outdoor_minutes`
- `page`
- `success` (boolean)

### `weather_looks` (~86 tokens)

Mes looks météo matin/midi/soir

Looks matin, midi, soir selon la météo locale. Ville/CP OU latitude+longitude. Je ne suppose jamais Paris.

Input parameters:

- `city` (string)
- `days` (integer): Forecast days, 1 to 7.
- `latitude`: Latitude, -90 to 90. Requires longitude.
- `longitude`: Longitude, -180 to 180. Requires latitude.

Output parameters:

- `days` (array)
- `error`
- `fetched_at`
- `message`
- `page`
- `place`
- `success` (boolean)
- `suggestions` (array)
- `timezone`
- `weather_source`

### `get_weather_context` (~128 tokens)

Je lis le bulletin

Faits météo seulement. Ville/CP OU lat+lon. question= peut porter la ville. Pas de repli silencieux sur Paris.

Input parameters:

- `at` (string): ISO 8601 or natural French time. Unreadable values return invalid_datetime.
- `latitude`: Latitude, -90 to 90. Requires longitude.
- `location` (string)
- `longitude`: Longitude, -180 to 180. Requires latitude.
- `occasion` (string)
- `outdoor_minutes` (integer): Minutes outside, 0 to 180.
- `question` (string)

Output parameters:

- `error`
- `limits`
- `location`
- `message`
- `privacy`
- `source`
- `success` (boolean)
- `suggestions` (array)
- `timezone`
- `weather`

### `recommend_weather_look` (~141 tokens)

Je croise circonstance et météo

Je croise la circonstance et le bulletin, ou je dis si la pièce tient. Passe question=. Jamais Paris par défaut. La ville n'est pas stockée.

Input parameters:

- `at` (string): ISO 8601 or natural French time.
- `latitude`: Latitude, -90 to 90. Requires longitude.
- `location` (string)
- `longitude`: Longitude, -180 to 180. Requires latitude.
- `occasion` (string)
- `outdoor_minutes` (integer): Minutes outside, 0 to 180.
- `piece` (string)
- `question` (string)
- `transport` (string)

Output parameters:

- `action`
- `circumstance`
- `error`
- `image`
- `limits`
- `location`
- `location_label`
- `message`
- `privacy`
- `reason`
- `recommendation`
- `source`
- `success` (boolean)
- `suggestions` (array)
- `timezone`
- `weather`

### `llms_guide` (~33 tokens)

Mon guide LLM

Carte ScoreLook pour les assistants : pages, hubs (dont chemisier), éditorial, règles de citation.

Output parameters:

- `error`
- `incident_id`
- `llms_txt_chars`
- `success` (boolean)
- `url`

### `proposer_demande_rappel` (~82 tokens)

Je prepare une demande de rappel style

Je prepare une demande de rappel (ecriture consentie). email ET consent=true obligatoires.
Retourne un action_id a confirmer par l'utilisateur (valable 10 minutes). Aucun enregistrement sans confirmation.

Input parameters:

- `consent` (boolean)
- `email` (string, required)
- `message` (string)
- `prenom` (string)

### `confirmer_action` (~43 tokens)

Je confirme une demande preparee

J'execute une demande preparee APRES confirmation explicite du visiteur (enregistre la demande et previent l'equipe).

Input parameters:

- `action_id` (integer, required)

### `annuler_action` (~29 tokens)

J'annule une demande preparee

J'annule une demande preparee non confirmee.

Input parameters:

- `action_id` (integer, required)

### `statut_actions` (~27 tokens)

Compteurs des ecritures preparees

Je renvoie les compteurs des ecritures preparees (aucune donnee personnelle).

## Diagnostics

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

## Score history

- 2026-10-03: 79
- 2026-10-02: 79
- 2026-10-01: 78
- 2026-09-30: 78
- 2026-09-29: 77
- 2026-09-28: 77
- 2026-09-27: 77
- 2026-09-26: 76
- 2026-09-25: 76
- 2026-09-24: 75
- 2026-09-23: 75
- 2026-09-22: 74
- 2026-09-21: 74

## Common questions

### What is the Capucine MCP server?

Capucine is an MCP server listed in the public MCP registry as fr.scorelook/capucine. Capucine, styliste IA ScoreLook : looks sourcés, météo, hubs pièces, critères shopping. This page covers its hosted endpoint (https://scorelook.fr/mcp).

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

Capucine scores 79 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 Capucine MCP server expose?

Capucine exposes 21 tools: manifest, search, fetch, recommend_look, shopping_criteria, and 16 more. Their descriptions and schemas cost roughly 1,652 tokens of context every time the server is loaded.

### Does the Capucine MCP server require authentication?

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

### Is the Capucine MCP server still maintained?

Capucine is still listed as active in the MCP registry. We last reached this channel on 3 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://scorelook.fr/mcp
- Website: https://scorelook.fr/scorelook-mcp
- Changelog RSS feed: https://verifymcp.io/servers/fr-scorelook-capucine/scorelook.xml
- Changelog JSON feed: https://verifymcp.io/servers/fr-scorelook-capucine/scorelook.json
- HTML version of this page: https://verifymcp.io/servers/fr-scorelook-capucine/scorelook