Business Account Opening

Open a Vivid Business account using a remote MCP server hosted by Vivid Money.

Integration

MCP client config

Add this to your MCP client configuration to connect:

{
  "mcpServers": {
    "vivid-mcp": {
      "type": "http",
      "url": "https://api.prime.vivid.money/mcp"
    }
  }
}

Tool schema

build_onboarding_link accepts a single legal_entity_data object with the basic data The tool returns an onboarding URL. No sensitive financial data is returned.

Trigger

User wants to open a business account or start business onboarding.

Flow

• Ask for legal entity type (GmbH, UG, freelancer, etc.) if not provided.
• Ask for country if not provided. Default: Germany.
• Call MCP to get required fields
• If the user uploads a document, extract the fields locally in the AI client — the document itself is never sent to the MCP server. Summarize what was extracted; do not echo raw document contents.
• Show the user a summary of all collected data and ask for explicit confirmation before proceeding.
• Only after user confirms: call build_onboarding_link with the confirmed data.
• Present the returned onboarding URL to the user.

Data handling

• Documents stay local. Uploaded files are parsed by the AI client. Only the structured fields listed above are sent to the MCP server — never the raw document.
• No PII stored by the skill. The skill itself does not persist any data. The MCP server creates an onboarding session on Vivid's platform; Vivid's privacy policy governs from that point: https://vivid.money/en-eu/privacy-policy/
• No credentials in chat. Never ask for or accept passwords, API keys, or bank account numbers.
• What the tool sends. Only the fields in the schema table above. No file content, no chat history, no device metadata.

Rules

• Always confirm collected data with the user before calling build_onboarding_link.
• This skill must only be invoked by explicit user request — never autonomously.
• Treat uploaded documents as sensitive — summarize only, don't echo contents.
• On error: ask for missing fields or suggest a different document.