Skip to main content
Glama
eu-kyb-mcp

eu-kyb-mcp

by mastermabel

Request a full company verification report (AgentSupply)

request_verification_report

Request a human-reviewed company verification report covering registry status, officers, VAT/LEI cross-checks, and red flags to validate a company before onboarding or payment.

Instructions

Sends a request to AgentSupply (https://agentsupply.dev), a third-party service, for a human-reviewed company verification report (registry status, officers, VAT/LEI cross-checks, red flags). The request content is transmitted to AgentSupply; a human reviews it and replies via the returned status_url or the contact email. Pilot service: nothing is charged without explicit agreement. Only call when the user wants this.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "company": "<company>"
    },
    "name": "request_verification_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyYesCompany name and country, or registry/VAT/LEI number
detailsNoWhat should be verified and why
contact_emailNoEmail for the reply (recommended)
monthly_volumeNoExpected number of reports per month, if recurring
max_price_per_reportNoMaximum price per report you would pay (EUR)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior5/5

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

Beyond annotations it discloses that request content leaves the system to a named third party, that a human reviews it asynchronously, and how the reply comes back (status_url or contact email). It also discloses the cost posture ('Pilot service: nothing is charged without explicit agreement'), which annotations cannot express. This is exactly the behavior an agent needs before making an outbound, non-idempotent request.

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 sentences, front-loaded with the service identity and URL, then the data-transmission fact, then the cost posture, then the call gate. No filler, though the closing 'Only call when the user wants this' is vague enough to be near-wasteful.

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

Completeness4/5

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

With no output schema, the description usefully explains how a result arrives (status_url / email reply), and it flags the external, human-mediated, non-idempotent nature of the call. It leaves turnaround time and any rate or volume limits unstated, which matters for a request-based service but is not fatal.

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?

Schema description coverage is 100%, so every parameter is already documented, making 3 the baseline. The description only slightly enriches semantics by tying contact_email to the reply channel; it adds nothing about company, details, monthly_volume, or max_price_per_report beyond the schema.

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 uses a concrete verb ('sends a request') and a concrete resource ('human-reviewed company verification report') and enumerates what the report covers (registry status, officers, VAT/LEI cross-checks, red flags). The framing as a human-reviewed, third-party request implicitly separates it from the instant lookups in the sibling set, though it never names an alternative explicitly.

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

Usage Guidelines3/5

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

'Only call when the user wants this' is a real but thin usage gate — it warns against unsolicited calls but doesn't say what 'wants this' means or when the sibling lookups (check_eu_vat, lookup_lei) suffice instead. The note that nothing is charged without explicit agreement supplies decision-relevant context but not when/when-not routing.

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