kromia-sdk (luishidalgoa/kromia-sdk) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 16 tools. No publisher has claimed this listing.

D
Caution
54/100

kromia-sdk

SDK contract-first del ecosistema Kromia: registries de recipes, slots, behaviors y actions en TypeScript que generan el contrato KRP versionado (JSON Schema) que consumen la web, la API y la app Flutter.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

luishidalgoa

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: KROMIA_TOKEN. We can’t prove the destination matches the brand the credential belongs to.
🚨
Known vulnerabilities in dependencies: 2 critical, 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 2 credentials: KROMIA_MCP_AUTH_TOKEN, KROMIA_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes16 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_recipes

Lista las recetas (plantillas de carta/sección) del modelo Kromia: id, kind (list/detail/expand), nombre y descripción. Punto de partida para diseñar una vista.

list_components

Lista los componentes prefabricados (bloques) que se pueden colocar en un layout.

list_field_types

Lista los tipos de campo del modelo (text, number, image, enum, rating…).

list_slot_kinds

Lista los slot-kinds (qué clase de contenido acepta un slot): id, label y descripción.

list_behaviors
list_effects

Lista los efectos visuales que se aplican a una carta según el VALOR de una tag (iridescent_foil, crown_badge, glow_border…): id, nombre, capa y cuántos parámetros tiene. Índice ligero: pide la ficha completa con describe(category:"visual-effect", id) antes de configurar ninguno. Los efectos son el

list_templates

Lista las plantillas de layout disponibles para una receta (id, nombre, descripción). Elegir + ajustar una plantilla existente da mejor resultado que diseñar el árbol desde cero.

describe

Devuelve la definición COMPLETA (incluida su doc: cuándo usar, slots, ejemplos) de un elemento del modelo: receta, componente, tipo de campo, slot-kind, behavior o efecto visual. Para `visual-effect` devuelve TODOS sus parámetros con tipo, opciones cerradas, min/max y default, más sus presets de fáb

validate_composition

Valida una ViewComposition (recipe + layout + slots) contra el modelo Kromia. Devuelve {valid, issues:[{path,message,level}]}. Úsalo en bucle: propón una composición → corrige los issues (usa el `path`) → repite hasta valid=true. `fieldDefs` (opcional) = los campos de la sección, para validar refere

validate_tag_styles

Valida un TagStyle[] (valor de una tag → efecto visual + su config) contra el catálogo real. Es el MISMO bucle corrector que validate_composition pero para el otro eje del diseño: devuelve {valid, issues:[{index,path,level,message}]}; corrige por el `path` y repite. Comprueba que el efecto existe, q

validate_album_data

Valida las CARTAS y los datos de sección contra el esquema: tipo, reglas del behavior, obligatorios, valores de enum y referencias entre secciones. Es la otra mitad del contrato — las demás tools validan cómo se VE el álbum, esta valida lo que CONTIENE. Úsala antes de entregar un lote de cartas: una

validate_rarity_source

Valida de qué campo sale la RAREZA y con qué reparto. La rareza es lo que convierte una lista de cartas en un coleccionable: gobierna qué cartas llevan efecto y cómo se componen los sobres, así que conviene fijarla al diseñar el esquema y no después. Comprueba que el campo existe y es elegible (pide

auto_compose

Genera una ViewComposition SENSATA a partir de los campos de la sección (heurística del SDK: mapea imagen/título/subtítulo/badge/stats a los slots correctos). `kind`: list o detail. Es el mejor punto de partida — luego ajústala con apply_template o a mano y re-valida. Devuelve {composition, validati

apply_template

Aplica una plantilla de layout (de las que devuelve list_templates para esa receta) a una composición existente, y valida. Enfoque ROBUSTO: elegir + ajustar una plantilla en vez de diseñar el árbol desde cero. Devuelve {composition, validation}.

get_template

Devuelve el árbol de layout que produce una plantilla para una receta, para INSPECCIONARLO antes de aplicarla. `slots` = ids de slots presentes (si se omite, se asumen todos).

apply_composition

Aplica una ViewComposition a la SECCIÓN de un ALBUM-schema de Kromia (las secciones viven en el album-schema, no en el card-schema). SEGURO: (1) valida localmente antes de nada; (2) DRY-RUN por defecto — muestra qué se aplicaría SIN escribir; solo escribe con `confirm:true`. Escribir requiere env `K

// known CVEs in dependencies2 critical3 high1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@2.1.0GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

criticalvitest@2.1.0GHSA-9crc-q9x8-hgqq

Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening

high@modelcontextprotocol/sdk@1.12.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configKROMIA_API_URL
🔐 secretKROMIA_MCP_AUTH_TOKENF4 ✅ — transporte remoto (Streamable HTTP) para agentes/terceros. Mismo set de tools servido por HTTP; stateful (sesión por mcp-session-id); auth Bearer opcional (). Endpoint POST/GET/DELETE /mcp.
configKROMIA_MCP_PORT
🔐 secretKROMIA_TOKENbackend. apply_composition sin se queda en dry-run y lo dice.
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

16/16 tools missing one or more hints — list_recipes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_components (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_field_types (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

11/16 tool handlers declare input schemas (69%)

Declare an inputSchema with zod/joi/yup on every tool definition.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

2 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Domain consistency

npm scope @kromia doesn't match GitHub owner luishidalgoa

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/luishidalgoa/kromia-sdk?variant=verified)](https://m8ven.ai/mcp/luishidalgoa/kromia-sdk)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 628e42831f4b110bf6fc68a0b10d41346be6c873
code hash: 46e5a14f72d142d6e74d0f42128b49d49805f665a23d517530baa319bc6b4a74
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client