de en es ja ko ru zh

koreafilings-mcp

Name: koreafilings-mcp
Author: OldTemple91

by OldTemple91

Overview Schema Source Related Servers Discussions Admin

Remote

Korea Filings

PyPI PyPI MCP License x402

Resúmenes en inglés listos para máquinas de las divulgaciones corporativas coreanas (DART · 전자공시), pagados por llamada en USDC a través del protocolo x402 en Base. Creado para agentes de IA, fondos cuantitativos y plataformas de investigación que necesitan acceso programático a los eventos del mercado coreano sin leer archivos PDF en coreano.

En vivo: https://koreafilings.com · API en https://api.koreafilings.com · documentación interactiva en /swagger-ui.

Qué hace

Los datos brutos de DART son gratuitos, pero están en coreano y estructurados para empleados humanos que presentan documentos, no para LLMs. Korea Filings convierte cada divulgación en una carga útil JSON estructurada, almacenada en caché y resumida en inglés: los agentes resuelven una empresa coreana por nombre de forma gratuita y luego obtienen un lote de resúmenes para ese ticker en una llamada pagada con x402. Cada resumen se ve así:

{
  "rcptNo": "20260424900874",
  "summaryEn": "Global SM's stock trading was temporarily suspended on April 24, 2026, due to a change in electronic registration related to a stock consolidation or split.",
  "importanceScore": 10,
  "eventType": "SINGLE_STOCK_TRADING_SUSPENSION",
  "sectorTags": ["Capital Goods"],
  "tickerTags": ["095440"],
  "actionableFor": ["traders", "long_term_investors"],
  "generatedAt": "2026-04-24T08:47:51Z"
}

La caché es la ventaja competitiva: el primer agente que solicita una divulgación paga el costo del LLM; cada agente posterior para el mismo rcpt_no accede a una búsqueda en la base de datos de costo casi nulo y sigue pagando la misma tarifa plana de 0.005 USDC por resumen. Las llamadas por lote de ticker acceden a la misma caché fila por fila, por lo que una llamada de cinco resúmenes equivale a cinco búsquedas en caché frente a un único pago en USDC transferido. Los márgenes aumentan a medida que crece la adopción.

Related MCP server: DART 공시 브리핑 MCP 서버

Cómo usarlo

Elija la interfaz que mejor se adapte a su stack. Las tres utilizan el mismo flujo x402 internamente; la billetera que firma el encabezado PAYMENT-SIGNATURE es la identidad. Sin claves API. Sin registro.

SDK de Python

pip install koreafilings

from koreafilings import Client

with Client(private_key="0x...", network="base") as client:
    # 1. Free name → ticker resolution
    matches = client.find_company("Samsung Electronics")
    ticker = matches[0].ticker  # "005930"

    # 2. Paid batch summary fetch (0.005 × limit USDC)
    filings = client.get_recent_filings(ticker, limit=5)
    for f in filings:
        print(f"[{f.importance_score}/10] {f.event_type}: {f.summary_en}")
    print("paid:", client.last_settlement.tx_hash)

Servidor MCP (Claude Desktop, Cursor, Continue, …)

uv tool install koreafilings-mcp

En la configuración de su cliente MCP:

{
  "mcpServers": {
    "koreafilings": {
      "command": "uv",
      "args": ["tool", "run", "koreafilings-mcp"],
      "env": {
        "KOREAFILINGS_PRIVATE_KEY": "0x...",
        "KOREAFILINGS_NETWORK": "base"
      }
    }
  }
}

Hay cinco herramientas disponibles: tres gratuitas para descubrimiento, dos pagadas:

find_company(query) — gratuita; búsqueda difusa de trigramas de 3,961 empresas que cotizan en KRX por nombre coreano, nombre en inglés o ticker.
list_recent_filings(limit) — gratuita; feed reciente de DART de todo el mercado (solo metadatos: deje que el agente decida por qué pagar).
get_pricing() — gratuita; billetera en vivo, red, contrato USDC, precio por endpoint.
get_recent_filings(ticker, limit) — pagada 0.005 × límite USDC; resúmenes de IA por lotes para un ticker, con el hash de la transacción de liquidación en cadena.
get_disclosure_summary(rcpt_no) — pagada 0.005 USDC; resumen único de IA para un número de recibo conocido.

El flujo natural del agente es find_company → get_recent_filings: una llamada gratuita para resolver un nombre a un ticker, una llamada pagada para obtener resúmenes para ese ticker.

curl / HTTP directo

# 1) Resolve a company name to a ticker. Free, no wallet needed.
curl 'https://api.koreafilings.com/v1/companies?q=Samsung+Electronics&limit=1'
#   HTTP/2 200
#   { "matches": [{ "ticker": "005930", "nameKr": "삼성전자",
#                   "nameEn": "SAMSUNG ELECTRONICS CO.,LTD.",
#                   "market": "KOSPI", ... }] }

# 2) Probe the paid endpoint without payment — server tells you the
#    exact USDC amount it wants for `limit=N` summaries.
curl -i 'https://api.koreafilings.com/v1/disclosures/by-ticker?ticker=005930&limit=3'
#   HTTP/2 402
#   payment-required: <base64 PaymentRequired payload, amount = 15000>
#   { "x402Version": 2, "accepts": [{ "scheme": "exact",
#       "amount": "15000", "asset": "USDC", "payTo": "0x8467…",
#       ... }], ... }

# 3) Sign an EIP-3009 TransferWithAuthorization for one of the entries
#    in `accepts`, base64-encode the signed PaymentPayload, and resend
#    with the PAYMENT-SIGNATURE header (x402 v2 transport spec).
#    See testclient/payer.py for a ~150-line reference implementation.
curl -H "PAYMENT-SIGNATURE: $SIGNED" \
     'https://api.koreafilings.com/v1/disclosures/by-ticker?ticker=005930&limit=3'
#   HTTP/2 200
#   payment-response: <base64 SettlementResponse with tx hash>
#   [ { "rcptNo": "...", "summaryEn": "...", "importanceScore": 7, ... },
#     { ... }, { ... } ]

El endpoint de tarifa plana de 0.005 USDC /v1/disclosures/summary?rcptNo=… sigue estando disponible para los llamadores que ya tienen un número de recibo de 14 dígitos: el mismo flujo x402, solo que con amount = 5000 y un cuerpo de resumen único.

Precios

Por llamada, en USDC en Base. Los endpoints gratuitos (/v1/companies, /v1/companies/{ticker}, /v1/disclosures/recent) no conllevan desafío de pago, por lo que un agente puede navegar antes de pagar.

Endpoint	Método	Precio (USDC)
`/v1/disclosures/by-ticker?ticker=…&limit=N`	GET	0.005 × N
`/v1/disclosures/summary?rcptNo=…`	GET	0.005

El precio por resultado en el endpoint por ticker se declara dinámicamente en el desafío 402: para limit=N, el servidor firma 0.005 × N USDC en accepts[0].amount para que el llamador vea el cargo exacto antes de autorizar la billetera. El endpoint de resumen único de tarifa plana se mantiene en 0.005 USDC y es la forma correcta cuando un llamador ya tiene un número de recibo de 14 dígitos de otro lugar.

El descriptor de precios completo legible por máquina (billetera actual, red, contrato USDC, cada endpoint pagado) se encuentra en /v1/pricing; el descubrimiento impulsado por agentes está en /.well-known/x402.

En vivo en Base mainnet a través del facilitador Coinbase CDP. La primera liquidación en cadena es permanente en 0x681c995e… — una billetera pagadora transfirió 0.005 USDC a la billetera del comerciante 0x8467Be164C75824246CFd0fCa8E7F7009fB8f720 en una única llamada transferWithAuthorization.

Arquitectura

Tres subsistemas lógicos comparten una aplicación Spring Boot:

Ingestión — programa una encuesta de 30 segundos contra la API abierta de DART, elimina duplicados por rcpt_no, persiste los metadatos brutos en Postgres, encola un trabajo de resumen.
Resumen — consume trabajos de resumen, clasifica la complejidad, enruta a Gemini 2.5 Flash-Lite (con limitación de tasa, disyuntor y reintentos de Resilience4j), persiste el resumen en inglés + etiquetas de ticker/sector + fila de auditoría en llm_audit.
API pagada — controlador Spring MVC detrás de un X402PaywallInterceptor. Cada solicitud: lee PAYMENT-SIGNATURE (o el alias heredado X-PAYMENT para clientes 0.2.x), verifica la firma con el facilitador, verifica Redis para evitar repeticiones, liquida en una respuesta 200 y adjunta PAYMENT-RESPONSE que lleva el hash de tx en cadena a través de un ResponseBodyAdvice. Si /settle falla o rechaza, el cuerpo se reescribe a la forma de falla de liquidación x402 v2 (HTTP 402 con la respuesta de liquidación de falla codificada en base64 en PAYMENT-RESPONSE y un cuerpo vacío) para que una interrupción del facilitador no pueda filtrar datos pagados sin pagar. El interceptor cortocircuita los métodos de controlador sin @X402Paywall, por lo que /v1/pricing, /.well-known/x402 y el documento OpenAPI permanecen sin autenticar.

El desafío 402 sigue la especificación de transporte x402 v2: el encabezado PAYMENT-REQUIRED lleva la carga útil PaymentRequired codificada en base64 (con la extensión bazaar que declara un esquema de entrada/salida para la capacidad de descubrimiento de agentes de IA), mientras que el cuerpo mantiene una copia JSON compatible con v1 para que los clientes más antiguos sigan funcionando.

Stack: Java 21, Spring Boot 3.4, PostgreSQL 16, Redis 7, Docker Compose, Cloudflare Tunnel, Cloudflare Workers. Consulte docs/ARCHITECTURE.md para notas más profundas.

Diseño del repositorio

.
├── src/                  # Spring Boot application source
├── sdk/python/           # `koreafilings` Python SDK (PyPI)
├── mcp/                  # `koreafilings-mcp` MCP server (PyPI)
├── landing/              # Marketing landing page (Cloudflare Workers)
├── testclient/           # Reference Python x402 client (testnet payer)
├── docs/
│   ├── ARCHITECTURE.md   # System design
│   ├── PRD.md            # Product requirements
│   ├── ROADMAP.md        # Six-week launch plan
│   └── STATUS.md         # Operator handoff notes
├── Dockerfile            # Multi-stage prod build (eclipse-temurin:21)
├── docker-compose.yml    # postgres + redis + app + cloudflared
└── build.gradle.kts      # Gradle (Kotlin DSL)

Desarrollo local

git clone https://github.com/OldTemple91/korea-filings-api.git
cd korea-filings-api

cp .env.example .env
# Fill in:
#   POSTGRES_PASSWORD     (any strong password)
#   DART_API_KEY          (free, register at https://opendart.fss.or.kr/)
#   GEMINI_API_KEY        (free tier, https://aistudio.google.com/apikey)
#   X402_RECIPIENT_ADDRESS (your receiving wallet — only the address)

docker compose up -d postgres redis
./gradlew bootRun

Para ejercer un pago x402 real contra una instancia local, copie testclient/.env.testclient.example a testclient/.env.testclient, complete la clave privada de una billetera (una billetera desechable nueva financiada con un dólar o dos de USDC de Base mainnet es el patrón seguro) y ejecute python testclient/payer.py. Para el desarrollo local contra el facilitador de testnet público, apunte X402_FACILITATOR_URL a https://www.x402.org/facilitator y use los parámetros de Base Sepolia en su .env.

Estado

En vivo en Base mainnet con liquidación en cadena verificada (primera tx). Conjunto de características MVP:

Ingestión de DART en tiempo real (encuesta de 30 segundos)
Resumen de Gemini 2.5 Flash-Lite con puntuación de importancia + etiquetado de sector/ticker
Muro de pago x402 v2 con extensión bazaar para invocación descubrible por agentes
Descubrimiento a través de /.well-known/x402
Especificación OpenAPI 3 en /v3/api-docs + interfaz Swagger interactiva
SDK de Python (koreafilings 0.3.1) y servidor MCP (koreafilings-mcp 0.3.0) en PyPI
Resolución gratuita de nombre → ticker (find_company) + feed reciente gratuito (list_recent_filings) para que los agentes puedan navegar antes de pagar
Endpoint de lote pagado por resultado (/v1/disclosures/by-ticker?ticker=…&limit=N) con 0.005 × N USDC declarado dinámicamente en el 402
Indexado por x402scan
Despliegue de producción en un VPS Linux a través de Cloudflare Tunnel
Facilitador Coinbase CDP (autenticación JWT Ed25519) para liquidación en mainnet

Limitación actual: cada resumen que el servicio produce hoy se genera solo a partir de metadatos de archivo: título, fecha, presentador, bandera DART. Eso es suficiente para mostrar el tipo de evento, la importancia y las etiquetas de ticker/sector ("detección de primera pasada"), pero no es suficiente para extraer números concretos como el tamaño de la oferta de derechos, el % de dilución o el valor del contrato. El LLM admite honestamente esto con frases como "los detalles están en el cuerpo del archivo" en lugar de inventar cifras.

Lo siguiente:

v1.2 — análisis profundo de archivos. Extraer el cuerpo del archivo a través del endpoint ZIP /document.xml de DART, analizar las plantillas XBRL para los seis tipos de eventos de mayor valor (RIGHTS_OFFERING, CONVERTIBLE_BOND_ISSUANCE, DEBT_ISSUANCE, ACQUISITION, SUPPLY_CONTRACT_SIGNED, MAJOR_SHAREHOLDER_FILING) y extraer montos, % de dilución, contraparte y fechas en un campo keyFacts estructurado. Nuevo endpoint pagado /v1/disclosures/deep?rcptNo=… en un nivel de precio más alto (~0.020 USDC): los endpoints existentes se mantienen solo con metadatos a 0.005 USDC para que los llamadores elijan la profundidad en el momento de la llamada. Detalle del roadmap en docs/ROADMAP.md.
POST /v1/disclosures/filter (consulta de sector + tipo de evento)
SSE /v1/disclosures/stream (push en tiempo real)
SDK de TypeScript
Página de aterrizaje en coreano
Alertas por Slack / correo electrónico sobre liquidación

Consulte docs/ROADMAP.md para el plan completo.

Contribución

Los problemas y PRs son bienvenidos, particularmente:

Puertos del SDK de Python a otros lenguajes (TypeScript, Go, Rust)
Endpoints de análisis adicionales (reacción de precio, archivos comparables, …)
Integraciones con frameworks de agentes que no sean x402
Traducción de la página de aterrizaje a otros idiomas

Para cambios sustanciales, por favor abra un problema primero describiendo la dirección para que podamos verificar la idoneidad antes de que construya.

Licencia

MIT.

Available Tools

5 tools

find_companyA

Search the KRX directory of Korean listed companies. Free.

Use this as the first step when you have a company name (English
or Korean) but not the six-digit KRX ticker. Pass the resulting
ticker to ``get_recent_filings`` (paid) or ``get_disclosure_summary``
(paid, when you also have a specific receipt number).

Args:
    query: Company name (English or Korean) or six-digit ticker.
        Examples: "Samsung Electronics", "삼성전자", "005930".
    limit: Max matches to return (1-50, default 20).

Returns:
    A list of company dicts with ``ticker``, ``corp_code``,
    ``name_kr``, ``name_en``, and ``market`` (KOSPI / KOSDAQ).
    Empty list when nothing matches; never raises on no-results.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses it is free, returns a list of dicts, and states behavior on no results ('Empty list... never raises'). Does not mention side effects but no issues expected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise with organized sections (intro, usage link, Args, Returns). Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool (2 params, no enums, has output schema), description covers purpose, usage, params, return format, and edge case (empty list). No gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but description adds examples for query (English, Korean, ticker) and specifies limit range (1-50, default 20), providing crucial context beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches the KRX directory for Korean listed companies, specifies the use case (getting a ticker from a company name), and distinguishes from siblings by mentioning passing to get_recent_filings or get_disclosure_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use this as the first step when you have a company name... but not the six-digit KRX ticker.' and provides follow-up usage, though does not explicitly state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_disclosure_summaryA

Fetch the AI-generated English summary of a Korean DART disclosure.

**This tool spends real USDC from the configured wallet** — 0.005
USDC per call as of v0.1, settled on-chain via x402. The wallet
pays only on a successful 200 response; 4xx/5xx failures do not
settle.

Args:
    rcpt_no: 14-digit DART receipt number, e.g. ``"20260424900874"``.
        You can discover receipt numbers from the DART portal at
        https://dart.fss.or.kr/ or from koreafilings.com's listing
        endpoints as they come online.

Returns:
    A dict with the summary content (``summary_en``), operational
    metadata (``importance_score`` 1–10, ``event_type``,
    ``ticker_tags``, ``sector_tags``, ``actionable_for``,
    ``generated_at``), and payment proof (``paid_tx``, ``network``,
    ``payer``). If the server served from its free-tier path the
    payment block is absent.

Raises:
    RuntimeError: when the SDK rejects the request. The message
        distinguishes payment failures (facilitator rejection,
        network mismatch, insufficient balance) from other API
        errors (404 unknown rcpt_no, 429 rate limit, 5xx upstream).

ParametersJSON Schema

Name	Required	Description	Default
`rcpt_no`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses the real USDC cost, settlement conditions, error handling, and return value structure including payment proof. This exceeds expectations for transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections and front-loaded with purpose and cost warning. It is somewhat lengthy but every sentence serves a clear purpose, earning a 4.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one parameter and an output schema, the description covers input, output structure, errors, cost, and use case. It is complete and leaves no gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter rcpt_no is documented with a 14-digit format, an example, and sources for discovery. Schema description coverage is 0%, but the description compensates fully, adding significant meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches an AI-generated English summary of a Korean DART disclosure. It specifies the resource (disclosure summary) and action (fetch), and is distinct from sibling tools like find_company or get_pricing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use (need a summary), provides cost and failure details, and tells how to discover receipt numbers. It lacks explicit when-not or alternative tools, but the context is sufficiently clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_pricingA

Fetch the current per-endpoint pricing for koreafilings.com.

This is a free call; it returns the x402 wallet address, network, USDC contract, and the price in USDC for each paid endpoint. Useful to confirm the payer will be settling on the expected chain before spending anything.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the call is free and returns specific fields (x402 wallet address, network, USDC contract, price in USDC). This gives good behavioral context, though it doesn't mention authentication or rate limits, which are likely unnecessary for a free, parameterless call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no wasted words. First sentence states purpose, second details output, third gives usage guidance. It is appropriately sized and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and the existence of an output schema (though not shown), the description mentions what the call returns and explains when to use it. It covers the necessary context for a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, and schema coverage is 100%, so baseline is 4. The description adds no extra parameter info because none exist, but that's appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool fetches current per-endpoint pricing for koreafilings.com. The verb 'Fetch' and resource 'current per-endpoint pricing' are specific. Sibling tools are about filings and disclosures, so this tool is distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description explicitly notes it's a free call and useful for confirming the payer will settle on the expected chain before spending. This implies when to use it, though it doesn't provide explicit exclusions or alternatives. Nevertheless, the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_recent_filingsA

Fetch up to limit AI summaries for one Korean ticker.

**This tool spends real USDC from the configured wallet** — 0.005
USDC × ``limit`` per call (default 0.025 USDC). The wallet pays
only on a successful 200 response; 4xx/5xx failures do not settle.

If you only have a company name, call ``find_company`` first to
resolve the ticker.

Args:
    ticker: Six-digit KRX ticker, e.g. "005930" for Samsung Electronics.
    limit: Max filings to fetch (1-50, default 5). Each costs 0.005 USDC.

Returns:
    A dict with ``ticker``, ``count``, ``summaries`` (each summary
    carries the same shape as ``get_disclosure_summary``), and a
    ``payment`` block with the on-chain settlement tx hash.

Raises:
    RuntimeError: on payment rejection or API failure.

ParametersJSON Schema

Name	Required	Description	Default
`ticker`	Yes
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries the burden, disclosing real USDC cost (0.005 per filing), payment on success only, return structure including payment tx hash, and RuntimeError on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence is purposeful: purpose, cost warning, usage hint, parameter descriptions, return shape, error handling. No redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (paid API with cost, two parameters, custom return), the description covers behavior, cost, error handling, and return shape comprehensively, despite no annotations or rich output schema in prompt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema description coverage, the description adds crucial details: ticker format with example, limit range (1-50) and default, and cost per unit, far exceeding schema's plain type info.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Fetch' and resource 'AI summaries for one Korean ticker', distinguishing it from siblings like find_company (resolves name to ticker) and list_recent_filings (likely just lists without costs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises to call find_company if only a company name is available, providing an alternative. No explicit when-not, but the cost implication implicitly guides against overuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_recent_filingsA

Browse recent DART filings across every listed Korean company. Free.

Returns metadata only — no AI summaries — so an agent can decide
which filings warrant a paid call. Each entry includes ``rcpt_no``
(for ``get_disclosure_summary``) and ``ticker`` (for
``get_recent_filings``).

Args:
    limit: Max filings to return (1-100, default 20).
    since_hours: Look back this many hours (1-168, default 24).

Returns:
    A list of filing-metadata dicts.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`since_hours`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states 'Returns metadata only' implying read-only behavior and mentions 'Free', but it does not explicitly confirm safety, idempotency, or authentication requirements. The description is mostly adequate but lacks explicit transparency on side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (6 sentences), well-structured with clear sections (purpose, return type, args, returns), and front-loads the primary purpose. Every sentence earns its place, with no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 optional parameters) and the presence of an output schema, the description is adequately complete. It covers metadata-only return and cross-references other tools, providing sufficient context for an agent to use this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description fully documents both parameters (limit and since_hours) with ranges and defaults, compensating for 0% schema description coverage. This adds meaning beyond the bare input schema, enabling precise agent decisions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool browses recent DART filings for Korean companies and returns metadata only. However, it does not differentiate itself from the sibling tool 'get_recent_filings', which has a similar name and purpose, creating potential ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description hints at a usage flow by referencing get_disclosure_summary for paid calls, but it does not explicitly state when to use this tool versus alternatives like get_recent_filings. It provides some context without clear when-to-use or when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

3 tool updatesv0.1.1Apr 29, 2026
- Addedfind_company
- Addedget_recent_filings
- Addedlist_recent_filings
2 tool updatesv0.1.0Apr 28, 2026
- First observedget_disclosure_summary
- First observedget_pricing

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.5/5.0

Scored 2026-09-09 18:52 across 5 tools

Disambiguation4/5

Each tool has a broadly distinct role: pricing lookup, company search, free filing metadata browsing, paid ticker-based summaries, and paid receipt-based summary retrieval. The main confusion risk is between list_recent_filings and get_recent_filings, whose names are very similar though their descriptions clearly separate free metadata browsing from paid AI summary generation.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern: get_pricing, find_company, list_recent_filings, get_recent_filings, get_disclosure_summary. The verbs are standard retrieval actions and the naming is uniform and predictable.

Tool Count5/5

Five tools is well-scoped for this server: pricing discovery, company resolution, free filing browsing, and two paid summary-fetching operations. Each tool earns its place and the server avoids unnecessary bloat.

Completeness4/5

The core workflow is covered: resolve a company with find_company, browse recent filings for free with list_recent_filings, then fetch paid AI summaries by ticker or receipt number. Minor gaps exist such as no historical filing lookup beyond recent limits and no raw disclosure document access, but these do not break the primary use case.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Concierge Intel C
xyz.conc-exe
Pay-per-call DeFi and macro intel for AI agents. x402 USDC tools via streamable HTTP /api/mcp.
Finance Blockchain
2
Inferventis — Financial Data, News & Web MCP A
io.github.jonathanpchapman
Live financial data MCP: FX, crypto, stocks, news, URL reader. x402 on Base: $0.001/call.
Finance Cryptocurrency Payments & Billing
202
1gateway
io.github.code0xff
x402 pay-per-call API gateway for AI agents (USDC on Base): Korean real estate, weather, holidays.
141
FinBridge AOAuth
kr.gronox.mcp
FinBridge is a hosted MCP server for Korean company disclosures, read in English. DART filings and normalized financial statements, business segments, insider reports and 13F holdings, with US, Japanese and European filers on the same schema for comparison. Search a company by its registered English name or its Korean name. Every answer names the filing, the receipt number and the date. Korean price delivery is planned and not currently served. Docs: https://www.gronox.kr/docs
Finance Open Data
1

Related MCP Servers

kr-crypto-intelligence
Cryptocurrency Finance Search
bakyang2
A
license
A
quality
C
maintenance
Korean crypto market data API for AI agents. Real-time Kimchi Premium (Upbit vs Binance), Korean exchange prices, USD/KRW FX rate. First verified Korean market data MCP server. Pay-per-use via x402 on Base.
Updated 2 months ago (2026-08-04 05:58 UTC)
17
2
MIT
DART 공시 브리핑 MCP 서버
Finance Government Data Search
iiacjay
F
license
Not graded
quality
D
maintenance
MCP server that searches and filters DART electronic disclosures for Korean companies, enabling AI agents to create investor briefing summaries.
Updated 3 months ago (2026-07-14 16:20 UTC)
-
Disclosure Compass
Finance Open Data Government Data
MLOpsEngineer
A
license
Not graded
quality
C
maintenance
A Model Context Protocol server that exposes seven read-only tools for querying Korean public company disclosures from the OpenDART system, returning normalized JSON.
Updated 3 months ago (2026-07-19 13:07 UTC)
MIT
OpenDart MCP Server
Finance Open Data
sayouzone
A
license
Not graded
quality
D
maintenance
An MCP server that retrieves Korean stock fundamentals and financial data from OpenDART, enabling LLMs to access corporate disclosures, financial statements, and dividend information.
Updated 8 months ago (2026-02-06 00:50 UTC)
Apache 2.0