Model Context Protocol (MCP)

Veilio integration guide for AI assistants, powered by KBrain.

Overview

The Model Context Protocol (MCP) lets AI assistants (Cursor, Claude Desktop, and others) connect to external knowledge sources while they help you.

Veilio provides an MCP server that exposes our integration guide. Instead of pasting documentation into every chat, you connect this server once and your assistant queries the Veilio knowledge base directly, for tokenization, the API, SDKs, compliance, and more.

Who is this for?

• Developers integrating Veilio into an existing application
• CTOs, DPOs, CISOs, and product teams who want to understand Veilio's security model
• Anyone building with AI coding assistants who wants accurate Veilio answers

What the Veilio MCP provides

Once connected, your assistant can use the search_knowledge tool to query the Veilio Guide brain before answering.

The guide covers:

• What Veilio is and how it protects sensitive data (tokenization, encryption, access control)
• Step-by-step integration workflows
• Audit logging, crypto-shredding, and secure data sharing

Note: This MCP complements static documentation and SDKs. It does not replace an API key or dashboard access.

Configuration

Prerequisites

• An MCP-compatible client: Cursor (v0.42+), Claude Desktop, or any tool that supports MCP over HTTP
• No authentication required (public endpoint)

Server URL

https://www.kbrain.io/api/mcp/open/kb-veilio-guide-mqj07vow

Cursor

1. Open Settings, then MCP, then Add new global MCP server (or edit your mcp.json file).
2. Add this configuration:

{
  "mcpServers": {
    "veilio-guide": {
      "url": "https://www.kbrain.io/api/mcp/open/kb-veilio-guide-mqj07vow",
      "transport": "streamable-http"
    }
  }
}

1. Restart Cursor if needed. A green indicator confirms the connection.

Global config path: ~/.cursor/mcp.json Project config path: .cursor/mcp.json at the repository root.

Claude Desktop

Edit your Claude Desktop config file and add the same JSON block as above.

macOS path: ~/Library/Application Support/Claude/claude_desktop_config.json

Example prompts

Once the MCP is connected, you can ask:

• How do I tokenize an email with the JavaScript SDK?
• What is the difference between tokenize and tokenizeBulk?
• How do I configure a retention policy and crypto-shredding?
• Which endpoints should I use to upload a CSV dataset?

The assistant queries the Veilio knowledge base before answering, which reduces hallucinations about the API.

About KBrain

This MCP is hosted by our partner KBrain. KBrain turns a knowledge base (guides, specs, FAQs) into an MCP endpoint usable by any compatible assistant. It allows experts, creators, and companies to package their knowledge, documentation, and best practices into reusable AI-ready Brains that can be used directly by ChatGPT, Claude, and AI agents. Instead of rewriting the same prompts and context repeatedly, users create a Brain once and make their expertise - including technical documentation and user guides - instantly accessible everywhere.

For classic documentation (API reference, SDKs, step-by-step guides), continue using docs.veilio.xyz. The MCP is an accelerator for AI-assisted integration.

Support

Technical questions: [e-mail]