Skip to main content
Glama

Corporate KYB & Compliance Risk Check

check_company_risk
Read-onlyIdempotent

Detect corporate KYB risks by screening insolvencies, sanctions, CNMV warnings, grants, and public contract awards from a CIF or company name.

Instructions

Perform corporate KYB compliance screening across BORME insolvencies, CNMV warnings, EU FSF sanctions, BDNS grants, and public contract awards. Costs $0.30 USDC or EURC per call via DATAX_TOKEN (returns HTTP 402 if unset). Requires cif and/or company_name (corporate tax/VAT IDs only; personal national IDs are blocked for GDPR). Returns risk_alert boolean, risk_level ('HIGH', 'LOW', or 'UNKNOWN'), hit counts by category, and item_ref handles ('dx_...') unlockable via get_tender_detail ($0.50).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_company_risk"
  }
}

Input Schema

NameRequiredDescriptionDefault
cifNoCorporate tax, VAT, or commercial registry identifier without spaces (e.g. 'B86900001'). Natural-person IDs are rejected per GDPR. Required if company_name is omitted.
company_nameNoRegistered corporate legal name (e.g. 'Indra Sistemas SA'). Required if cif is omitted; supply both for broader matching.

Output Schema

NameRequiredDescriptionDefault
resultNo
statusNo
change_tokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.2
    • addedInput schema / properties / cif / description
      Added value: +"Corporate tax, VAT, or commercial registry identifier without spaces (e.g. 'B86900001'). Natural-person IDs are rejected per GDPR. Required if company_name is omitted."
    • addedInput schema / properties / company_name / description
      Added value: +"Registered corporate legal name (e.g. 'Indra Sistemas SA'). Required if cif is omitted; supply both for broader matching."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "change_token": {
      +      "type": "string"
      +    },
      +    "result": {
      +      "properties": {
      +        "data_version": {
      +          "type": "string"
      +        },
      +        "operation": {
      +          "type": "string"
      +        },
      +        "risk_alert": {
      +          "type": "boolean"
      +        },
      +        "risk_level": {
      +          "type": "string"
      +        },
      +        "signals": {
      +          "items": {
      +            "properties": {
      +              "ambito": {
      +                "description": "Geographic jurisdiction or region.",
      +                "type": "string"
      +              },
      +              "detail_locked": {
      +                "description": "Always true until unlocked with get_tender_detail.",
      +                "type": "boolean"
      +              },
      +              "fecha_pub": {
      +                "description": "Publication date in YYYYMMDD format.",
      +                "type": "string"
      +              },
      +              "importe_texto": {
      +                "description": "Formatted amount string when available.",
      +                "type": "string"
      +              },
      +              "item_ref": {
      +                "description": "Opaque encrypted record reference ('dx_...') for get_tender_detail.",
      +                "type": "string"
      +              },
      +              "notice_type": {
      +                "description": "Notice classification.",
      +                "type": "string"
      +              },
      +              "preview": {
      +                "description": "Redacted summary preview without PII or entity identifiers.",
      +                "type": "string"
      +              },
      +              "seccion": {
      +                "description": "Registry section code.",
      +                "type": "string"
      +              },
      +              "unlock_price_micros": {
      +                "description": "Unlock price in USD/EUR micros (500000 = 0.50).",
      +                "type": "integer"
      +              }
      +            },
      +            "type": "object"
      +          },
      +          "type": "array"
      +        },
      +        "summary": {
      +          "type": "object"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "status": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing the paid-call model ($0.30 USDC or EURC), the DATAX_TOKEN credential requirement and the HTTP 402 failure mode, and the GDPR restriction rejecting natural-person IDs. These are exactly the operational facts an agent needs before invoking a metered open-world tool.

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?

Four dense sentences, front-loaded with purpose, then cost/credential, then input constraints, then return contract — a logical order with no filler. Minor deduction: because an output schema exists, the enumerated return fields are partly redundant, though the item_ref/get_tender_detail linkage still earns its place.

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?

For a metered, credential-gated screening tool the description covers purpose, payment and auth failure mode, input preconditions, GDPR limits, and how to follow up on results. With an output schema present and 100% parameter coverage, nothing an agent needs to call it correctly is missing.

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 both parameters are already documented, making 3 the baseline. The description however adds the crucial constraint that at least one of the two must be supplied ('and/or'), which the schema does not express since required is empty and there is no anyOf — that is genuine added 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?

States a specific verb+resource ('corporate KYB compliance screening') and enumerates the exact source registries covered (BORME, CNMV, EU FSF, BDNS, contract awards). An agent can immediately tell this apart from search_tenders or find_distressed_auctions.

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?

Gives the input precondition ('requires cif and/or company_name') and routes the agent to a named next step, get_tender_detail, to unlock the returned item_ref handles. It does not explicitly state when to prefer this over siblings like find_distressed_auctions, but the screening intent is clear from context.

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