Skip to main content
Glama
deenesjakoruzh
traql

traql MCP server

Official
by traql
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

traql MCP server

npm CI License: MIT

Puntuación de riesgo AML y de cumplimiento para direcciones y transacciones de criptomonedas, expuesta a agentes de IA a través del Model Context Protocol.

Pregunta a tu agente "¿es seguro enviar a esta dirección?" y obtendrás una puntuación de riesgo de 0–100, una banda, las categorías de riesgo asociadas y, con una clave de API, cada señal individual con su fuente y nivel de confianza.

ethereum address 0x8589427373d6d84e98730d7795d8f6f8731fda16
RISK 100/100 — CRITICAL
Flags: sanctions, mixer, scam

Signals (21):
  +80  [sanctions/eth_labels] direct.sanctions — sanctions label "Tornado.Cash: Donate" [entity Tornado.Cash: Donate, confidence 0.80]
  +68  [mixer/eth_labels] direct.mixer — mixer label "Tornado.Cash: Donate" [entity Tornado.Cash: Donate, confidence 0.80]
  +10  [mixer] behavior.mixer_contact — direct contact with mixer 0xdd4c48c0b24039969fc16d1cdf626eab821d3384
  +9   [sanctions/ofac_sdn] indirect.sanctions — sent to Semenov Roman (sanctions, 18% of USDC volume) [entity Semenov Roman, confidence 1.00]
  ... and 17 more

Computed at 2026-08-23T11:42:49Z.

Con el respaldo de traql: listas de sanciones de OFAC SDN, OFSI del Reino Unido, la UE y la ONU, eventos de congelación de Tether/Circle, atribuciones seleccionadas de hacks y mezcladores, y análisis de exposición de contrapartes en Ethereum, BSC, TRON, TON y Bitcoin.

Inicio rápido

Requiere Node.js 18+.

npx -y @traql/mcp

El servidor habla MCP sobre stdio, así que normalmente apuntarás un cliente hacia él en lugar de ejecutarlo manualmente.

Claude Code

claude mcp add traql --env TRAQL_API_KEY=your_key -- npx -y @traql/mcp

Claude Desktop

Añade a claude_desktop_config.json:

{
  "mcpServers": {
    "traql": {
      "command": "npx",
      "args": ["-y", "@traql/mcp"],
      "env": { "TRAQL_API_KEY": "your_key" }
    }
  }
}

Cursor

Añade a ~/.cursor/mcp.json (o .cursor/mcp.json en un proyecto) usando el mismo bloque mcpServers de arriba.

VS Code

Añade a .vscode/mcp.json:

{
  "servers": {
    "traql": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@traql/mcp"],
      "env": { "TRAQL_API_KEY": "your_key" }
    }
  }
}

Related MCP server: zarq-risk-intelligence

Cómo obtener una clave de API

Regístrate en app.traql.io, confirma tu correo electrónico — se incluyen comprobaciones gratuitas — y emite una clave en API keys. El secreto se muestra una sola vez; se puede rotar o revocar en cualquier momento.

Sin clave, el servidor sigue funcionando, pero en el modo sin clave: una única frase de motivo general en lugar de señales detalladas, límites de solicitud estrictos y, en la API alojada, un requisito de pago por llamada x402. Para uso con agentes, configura una clave.

Configuración

Variable

Requerido

Por defecto

Descripción

TRAQL_API_KEY

recomendada

—

Clave de API del panel de traql. Se envía como X-API-Key. Desbloquea señales detalladas y límites más altos.

TRAQL_API_URL

no

https://api.traql.io

URL base de la API. Apúntala a tu propio despliegue si autoalojas traql.

TRAQL_TIMEOUT_MS

no

30000

Tiempo máximo de espera por solicitud en milisegundos.

Herramientas

check_address

Puntúa una sola dirección.

Argumento

Tipo

Requerido

Descripción

chain

ethereum | bsc | tron | ton | bitcoin

sí

Red a la que pertenece la dirección.

address

string

sí

Dirección en el formato nativo de la cadena.

screen_transaction

Puntúa ambos lados de una transferencia, en uno de dos modos:

  • Pre-flight — pasa from y to (opcionalmente amount y asset) para evaluar una transferencia antes de emitirla. Funciona en todas las cadenas compatibles.

  • Por hash — pasa únicamente tx_hash para consultar una transacción que ya está en cadena. Compatible con Ethereum, BSC, TRON y TON.

Argumento

Tipo

Requerido

Descripción

chain

cadena enum

sí

Red a la que pertenece la transacción.

from

string

pre-flight

Dirección del remitente.

to

string

pre-flight

Dirección del destinatario.

amount

string

no

Cantidad entera en las unidades base del activo (p. ej., 1000000 para 1 USDT).

asset

string

no

Símbolo del activo o token, p. ej. USDT.

tx_hash

string

por hash

Hash de una transacción emitida. Es mutuamente excluyente con from/to.

Respuesta

Ambas herramientas devuelven texto legible por humanos y structuredContent:

{
  "subject": { "type": "address", "chain": "ethereum", "address": "0x…" },
  "result": {
    "score": 100,
    "band": "critical",
    "flags": ["sanctions", "mixer", "scam"],
    "partial": false,
    "computed_at": "2026-08-23T11:42:49Z",
    "reasons": [
      {
        "code": "direct.sanctions",
        "message": "sanctions label \"Tornado.Cash: Donate\" from eth_labels (severity 100 × confidence 0.80 = 80.0)",
        "contribution": 80,
        "category": "sanctions",
        "source": "eth_labels",
        "entity": "Tornado.Cash: Donate",
        "severity": 100,
        "confidence": 0.8,
        "eff": 80.0
      }
    ]
  }
}

Bandas de puntuación: clean 0–9, low 10–39, elevated 40–69, high 70–89, critical 90–100.

partial: true significa que una fuente de datos anterior estaba degradada al calcular el resultado; interpreta la puntuación como un límite inferior, no como un veredicto final.

Cada llamada correcta consume una verificación de la cuenta configurada. La entrada malformada se rechaza localmente cuando es posible, por lo que no cuesta nada.

Desarrollo

npm install
npm run build
npm test

Notas

Las puntuaciones son señales orientativas para la priorización y la automatización. No constituyen una determinación legal de irregularidad y, por sí mismas, no eximen de ninguna obligación regulatoria.

Enlaces

Licencia

MIT

Available Tools

2 tools
check_addressCheck address riskA
Read-only

Score a single crypto address for AML and compliance risk.

Returns a risk score from 0 (clean) to 100 (critical), the band it falls into, and the risk categories that drove it — sanctions, mixer, scam, darknet, stolen_funds, ransomware, high_risk_exchange and others. With an API key configured, the response also itemizes every contributing signal with its data source, severity and confidence, so the verdict can be explained rather than just asserted.

Use it before sending funds to an unfamiliar address, to triage an address a user pasted, to check a counterparty in an investigation, or to vet a deposit address. Covers Ethereum, BSC, TRON, TON and Bitcoin. Each call consumes one check from the configured traql account.

ParametersJSON Schema
NameRequiredDescriptionDefault
chainYesBlockchain network the subject belongs to.
addressYesAddress in the chain's native format: 0x-hex for ethereum and bsc, base58 starting with T for tron, EQ/UQ for ton, and legacy or bech32 for bitcoin.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
subjectYesEcho of the canonical subject that was scored.

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already indicate readOnlyHint and non-destructive, and the description adds meaningful behavioral detail beyond that: the exact return semantics (risk score 0-100, bands, categories), conditional verbosity with an API key, and the resource cost ('Each call consumes one check'). It doesn't contradict annotations, and the additional consumption caveat is valuable.

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 front-loaded with the purpose and returns, then use cases, then chains and consumption. It is concise at four sentences, with no fluff. It could be slightly tighter (the chain list is redundant with the schema enum), but it remains efficiently structured and readable.

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 presence of an output schema, the description need not detail return types, but it still explains the risk score range, band concept, and categories. It also covers supported chains, use cases, and the API-key enhancement. Everything an agent needs to invoke and interpret the result is present, so it is fully complete.

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

Parameters3/5

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

The input schema already provides full descriptions for both parameters (chain enum and address format), so the baseline is 3. The description adds no extra parameter semantics—it only references the chain coverage implicitly, which the schema already communicates. No additional meaning is introduced beyond the 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 begins with a clear verb-resource pair ('Score a single crypto address for AML and compliance risk') that precisely states the tool's function. It also differentiates from the sibling tool screen_transaction by focusing on address-level vetting rather than transaction screening.

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 lists concrete use cases ('before sending funds', 'triage a pasted address', 'vet a deposit address'), giving clear context for when to use it. It does not explicitly exclude transaction screening, but the single sibling tool makes the distinction evident; mentioning that tool as an alternative would make this a perfect 5.

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

screen_transactionScreen transaction riskA
Read-only

Screen a transaction for AML and compliance risk by scoring both sides of the transfer.

Two modes, chosen by which arguments are given:

  • Pre-flight — pass from and to (optionally amount and asset) to screen a transfer before it is broadcast. Works on every supported chain.

  • By hash — pass only tx_hash to look up a transaction that is already on-chain. Supported on ethereum, bsc, tron and ton.

Returns the same score, band, flags and itemized signals as an address check, with each signal marked as applying to the sending or receiving side. Use it as a pre-send safety gate, or to review a payment that already went out. Each call consumes one check from the configured traql account.

ParametersJSON Schema
NameRequiredDescriptionDefault
toNoRecipient address, for screening a transfer that has not been broadcast yet.
fromNoSender address, for screening a transfer that has not been broadcast yet.
assetNoOptional asset or token symbol being transferred, for example USDT.
chainYesBlockchain network the subject belongs to.
amountNoOptional transfer amount as an integer string in the asset's base units (for example 1000000 for 1 USDT, which has 6 decimals). Never a decimal fraction.
tx_hashNoHash of an already-broadcast transaction. Mutually exclusive with `from`/`to`. Supported on ethereum, bsc, tron and ton only.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
subjectYesEcho of the canonical subject that was scored.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context beyond annotations: 'Each call consumes one check from the configured traql account' (a quota side effect) and describes the return structure ('score, band, flags and itemized signals'). This is consistent with annotations and provides useful operational detail.

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?

Well-structured with a clear opening statement followed by a bulleted breakdown of modes. The information is front-loaded and each sentence serves a purpose—no filler or redundancy. It is slightly long but contains only necessary details, earning a 4 rather than 5 due to the length.

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 (two modes, six parameters, chain restrictions, and an existing output schema), the description covers all essential usage context: modes, which chains support which mode, use cases, and the quota side effect. Nothing critical is missing for an agent to invoke it correctly.

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?

Schema coverage is 100%, so the baseline is 3. The description adds meaning by explaining the two modes and how parameters relate (pre-flight: from/to, optional amount/asset; by-hash: tx_hash only, mutually exclusive). It also gives an example for the amount format, reinforcing the schema description. This is helpful clarification beyond the schema's individual parameter descriptions.

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 opens with a clear verb+resource: 'Screen a transaction for AML and compliance risk by scoring both sides.' It explicitly differentiates from the sibling address-check tool by focusing on transactions and even references the shared return format ('same score, band, flags and itemized signals as an address check'). This leaves no ambiguity about what the tool does and how it differs from check_address.

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 clearly states when to use it: 'Use it as a pre-send safety gate, or to review a payment that already went out.' It also details two explicit modes with the exact parameters to pass ('pass from and to...' vs 'pass only tx_hash') and lists chain support for each. While it doesn't explicitly name check_address as an alternative, the mention of 'same... as an address check' implies routing, so guidance is strong but not exhaustive.

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.

  1. 2 tool updatesv0.1.0
    • First observedcheck_address
    • First observedscreen_transaction
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

A4.4/5.0

Scored across 2 tools

Disambiguation5/5

The two tools target distinctly different entities: check_address evaluates a single address, while screen_transaction evaluates a transaction by scoring both sides. They are clearly separated by purpose and input requirements, with no overlapping functionality.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern: check_address and screen_transaction. The verbs ('check' vs 'screen') are semantically appropriate and the noun targets (address, transaction) are clear, maintaining a uniform naming style.

Tool Count4/5

With only two tools, the server is compact but well-scoped for its narrow AML screening purpose. Each tool covers a fundamental operation (address check and transaction screening), so the count feels appropriate rather than insufficient, though it is below the typical 3-15 range.

Completeness4/5

The tool surface covers the primary use cases for AML risk assessment: pre-transaction screening and single-address checks. Minor gaps exist, such as lack of batch processing or historical investigation features, but these are not essential for the stated purpose and do not create dead ends in common workflows.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • BICScan MCP Server

    ahnlabio
    A
    license
    B
    quality
    D
    maintenance
    Provides blockchain address risk scoring and asset information through the BICScan API, allowing users to assess risks for crypto addresses, domains, and dApps on a scale of 0-100.
    2
    16
    MIT

  • BlackSwan MCP Server

    blackswanwtf
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to access real-time crypto risk intelligence with two tools: Flare for precursor detection and Core for overall risk environment assessment.
    4
    -

  • OceanAlt AML

    OceanAlt
    A
    license
    Not graded
    quality
    C
    maintenance
    Crypto compliance tools for AI-agent payments: screen any address for sanctions, frozen-stablecoin and hacker/mixer exposure across 8+ chains, trace fund taint, and get an allow/review/decline decision before settlement. Free keyless address checks; deeper endpoints are x402-payable.
    314 npm
    MIT