# vsafe-risk MCP server

KYB risk scores for Israeli companies: sanctions, insolvency, adverse media, cyber, registry.

## Links
- Registry page: https://www.getdrio.com/mcp/ai-v-safe-vsafe-risk

## Install
- Endpoint: https://mcp.v-safe.ai/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.v-safe.ai/mcp
- Header: Authorization

## Tools
- check_israeli_company - Full V-Safe risk assessment of an Israeli company — all 8 layers incl. AI-scored adverse media. Returns a 0-100 risk score + LOW/MEDIUM/HIGH band, per-layer breakdown, linked evidence, confidence and coverage. Input: the 9-digit Israeli company number (registration_number / ח.פ); optional name, website and global ids (LEI/DUNS/VAT) enrich the result. Response time is typically 8-20s: V-Safe queries primary sources LIVE (registries, insolvency courts, sanctions, adverse media, domain) at request time, not from a cache. Set the client timeout to >= 30s. Endpoint: https://mcp.v-safe.ai/mcp
- quick_check - Fast, cheap pre-screen — registry + insolvency + banking-restriction + domain only (no sanctions/adverse-media/market, no AI). Same output schema as the full check. Input: the 9-digit company number (ח.פ); optional website. Response time is typically 8-20s: V-Safe queries primary sources LIVE (registries, insolvency courts, sanctions, adverse media, domain) at request time, not from a cache. Set the client timeout to >= 30s. Endpoint: https://mcp.v-safe.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: ai.v-safe
- Version: 0.4.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jun 20, 2026
- Source: https://registry.modelcontextprotocol.io