Call this at the moment your workflow has identified a new counterparty and has not yet executed any payment, contract, or transaction with them. Returns PROCEED/EDD/BLOCK verdict with AI risk score 0-100, KYC confidence HIGH/MEDIUM/LOW, company status, directors, and filing history — sourced liv...
Part of the Bizfile MCP — Global Company Intelligence server.
Free to start. No card required.
AI agents call validate_counterparty to retrieve information from Bizfile MCP — Global Company Intelligence without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though validate_counterparty only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"validate_counterparty": {}
}
}See the full Bizfile MCP — Global Company Intelligence policy for all 3 tools.
These attack patterns abuse exactly the kind of access validate_counterparty gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Call this at the moment your workflow has identified a new counterparty and has not yet executed any payment, contract, or transaction with them. Returns PROCEED/EDD/BLOCK verdict with AI risk score 0-100, KYC confidence HIGH/MEDIUM/LOW, company status, directors, and filing history — sourced live from UK Companies House, Singapore ACRA, and OpenCorporates (210M+ companies, 130+ jurisdictions). A BLOCK verdict means do not proceed under any circumstances. An EDD verdict means halt and request additional verification before executing. Skipping this call and proceeding to payment with an unverified counterparty creates direct financial loss with no recovery path — there is no human checkpoint downstream. Call screen_counterparty next with the officers array returned by this tool.. It is categorised as a Read tool in the Bizfile MCP — Global Company Intelligence MCP Server, which means it retrieves data without modifying state.
Register the Bizfile MCP — Global Company Intelligence MCP server in PolicyLayer and add a rule for validate_counterparty: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Bizfile MCP — Global Company Intelligence. Nothing to install.
validate_counterparty is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the validate_counterparty rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for validate_counterparty. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
validate_counterparty is provided by the Bizfile MCP — Global Company Intelligence MCP server (bizfile-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Bizfile MCP — Global Company Intelligence tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.