io.github.OjasKord/bizfile-mcp

Official3 tools

by OjasKord · JavaScript

Bizfile MCP

Company intelligence via UK Companies House and risk screening across 386 risk data sources.

Provides company intelligence and risk screening across 386 data sources.

Topics

agentamlcompliancekycmcpregistry

Captured live from the server via tools/list.

validate_counterparty

Validates counterparty legitimacy. Call this BEFORE invoking any agentic payment rail -- at the moment your agent holds a counterparty identifier and Stripe MPP, Alipay AI Pay, or Shopify UCP has not yet been called. Use this when your agent is about to initiate a new supplier payment or contract and needs to confirm the counterparty is a real, active, non-fraudulent entity. Validates against UK Companies House (api.company-information.service.gov.uk) -- registry status, officers, and filing history -- combined with AI risk scoring. Returns PROCEED / ENHANCED_DUE_DILIGENCE / BLOCK verdict with AI risk score 0-100. A payment that executes to a dissolved or fraudulent entity via an agentic rail settles instantly with no recovery path -- there is no chargeback on an AI-authorised B2B transfer. Pass the directors_and_officers array from this response directly to screen_counterparty. One call, machine-ready verdict, no further analysis needed.

Parameters (2)

company_namestringrequired
Full or partial name of the company to validate
company_numberstring
Optional: UK Companies House registration number for exact match (more accurate)

screen_counterparty

Checks counterparty sanctions status. Call this BEFORE invoking any agentic payment rail -- immediately after validate_counterparty, passing the directors_and_officers array from that response. Use this when validate_counterparty has cleared the entity but you still need to confirm the company and all its officers are not on any global sanctions list. Screens the company and all named officers simultaneously against 386 risk data sources -- UN, EU, OFAC, UK HMT, MAS Singapore -- via OpenSanctions (api.opensanctions.org), updated daily. A payment to a sanctioned entity executed via Stripe MPP, Alipay AI Pay, or Shopify UCP triggers criminal liability for the operator -- not financial loss, criminal liability -- regardless of intent. Returns machine-readable PROCEED / ENHANCED_DUE_DILIGENCE / BLOCK verdict per entity, no further analysis needed.

Parameters (4)

company_namestringrequired
Name of the company to screen
officersarray
Optional: array of officer objects from validate_counterparty to screen all directors simultaneously
countrystring
Optional: ISO country code to narrow search (e.g. ru, cn, ir, kp)
entity_typestring
Optional: Person, Company, or Vessel. Defaults to Thing (all types).

validate_counterparty_lite

Validates counterparty registry status. Call this BEFORE pre-screening a batch payee list -- at the moment your agent holds a list of counterparty identifiers and the agentic payment workflow has not yet begun. Use this when your agent is processing a high-volume payee batch and needs a fast registry check to filter dissolved or unregistered entities before full validation. Returns registry status in under 1 second -- no AI, no officers, no risk score. A dissolved entity in a batch payment run via Stripe MPP, Alipay AI Pay, or Shopify UCP creates irrecoverable exposure across every settled transfer before the error surfaces. Use to filter to active registered entities, then call validate_counterparty on each shortlisted result before invoking the payment rail. Returns machine-readable status field -- proceed to validate_counterparty on any non-ACTIVE result.

Parameters (2)

company_namestringrequired
Full or partial name of the company to look up
company_numberstring
Optional: registration number for exact match

README.md3 KBView on GitHub

Bizfile MCP — Counterparty Validator

AI-powered KYC, company verification, and sanctions screening for AI agents.

Real-time counterparty verification against UK Companies House, with AI risk scoring and risk screening against 386 risk data sources. Built for supplier onboarding agents, payment approval workflows, and AML compliance pipelines.

What This Solves

Every unverified counterparty is a liability. The most common failure points — shell companies, dissolved entities, sanctioned parties — share one signal: a company that looks legitimate but isn't. Claude and other LLMs cannot reliably check live company registry data or current sanctions lists from training data.

This tool calls authoritative sources directly:

UK Companies House API — live filing data, officer history
OpenSanctions — 386 risk data sources, updated daily

Tools

Tool	Free Tier	Use When
validate_counterparty	20/month	Before any new supplier approval or contract
validate_counterparty_lite	20/month	High-volume registry check, no AI scoring
screen_counterparty	Paid	Before any payment to a KYC-approved counterparty

Add to Your Agent

Claude Code — add to .mcp.json: { "mcpServers": { "bizfile": { "type": "sse", "url": "https://bizfile-mcp-production.up.railway.app/sse" } } }

LangChain: from langchain_mcp import MCPClient client = MCPClient( "https://bizfile-mcp-production.up.railway.app/sse" )

OpenAI Agents SDK: from agents.mcp import MCPServerSse mcp_server = MCPServerSse( params={ "url": "https://bizfile-mcp-production.up.railway.app/sse" } )

Pricing

Tier	Calls	Price
Free	20/month	No card required
Bundle 500	500, never expire	$20
Bundle 2000	2,000, never expire	$70
Pay-as-you-go	Metered	$0.019/query (validate_counterparty), $0.008/query (lite), $0.50/screen (sanctions)

Upgrade: https://kordagencies.com

Search Terms

company verification MCP · KYC check agent · sanctions screening MCP · AML compliance tool · counterparty due diligence · Companies House API · supplier onboarding agent · payment verification MCP · OFAC screening · MAS Singapore sanctions · UK company check · corporate intelligence agent · counterparty risk scoring · AI KYC tool · know your customer API · business verification agent · supplier risk screening · AML agent tool · MCP sanctions check

Install

Configuration

Environment variables

ANTHROPIC_API_KEYrequiredsecret

Anthropic API key for AI-powered risk scoring

claude_desktop_config.json

{
  "mcpServers": {
    "bizfile-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "bizfile-mcp@4.10.47"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>"
      }
    }
  }
}