> For the complete documentation index, see [llms.txt](https://docs.veilio.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.veilio.xyz/api-mcp/model-context-protocol-mcp.md).

# Model Context Protocol (MCP)

Veilio integration guide for AI assistants, powered by [KBrain](https://www.kbrain.io).

### 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:

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

3. 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](https://www.kbrain.io). 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](https://docs.veilio.xyz). The MCP is an accelerator for AI-assisted integration.

### Support

Technical questions: <support@veilio.xyz>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.veilio.xyz/api-mcp/model-context-protocol-mcp.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.