If you build AI agents in Cursor, Claude Desktop, or VS Code, you can manage your entire Kynver presence without ever leaving your coding environment — registering agents, checking verification status, starting KYC, even getting ready-to-use tracking setup code.
What Is the Kynver MCP Server?
MCP stands for Model Context Protocol — a standard that lets AI coding tools connect to external services as tools the AI can call on your behalf.
The Kynver MCP server gives your AI assistant a set of Kynver-specific tools: - Register an agent on Kynver without filling out a form - Look up any agent — profile, trust score, verification status - Advance your verification — start KYC, pass the ownership challenge, submit the questionnaire - Get execution tracking setup code pre-filled with your agent's DID
In plain terms: your AI assistant becomes a hands-free way to manage your Kynver account while you are building.
What You Need Before Starting
- Node.js 18 or later on your computer. Not sure if you have it? Open a terminal and type node --version. If you see something like v20.x.x, you are set. If not, download it from nodejs.org and restart your IDE after installing.
- Cursor, Claude Desktop, or VS Code with GitHub Copilot.
- A Kynver account.
- A Kynver API key if you want write tools (register, verify, etc.). Read-only tools work without one.
Setting Up in Cursor
Option A — using the settings UI: - Open Cursor → Settings → MCP → Add new MCP server - Name: kynver, Command: npx, Arguments: -y @kynver-app/mcp-server - Add an env var: KYNVER_API_KEY = your key - Save. Cursor downloads and starts the server automatically.
Option B — using a config file. Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"kynver": {
"command": "npx",
"args": ["-y", "@kynver-app/mcp-server"],
"env": {
"KYNVER_API_KEY": "<your-api-key>"
}
}
}
}Leave out the KYNVER_API_KEY line entirely if you do not have one yet — read-only tools still work.
Setting Up in Claude Desktop
{
"mcpServers": {
"kynver": {
"command": "npx",
"args": ["-y", "@kynver-app/mcp-server"],
"env": {
"KYNVER_API_KEY": "<your-api-key>"
}
}
}
}Config file location: - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json - Windows: %APPDATA%\Claude\claude_desktop_config.json
Setting Up in VS Code
Create .vscode/mcp.json in your project root:
{
"servers": {
"kynver": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@kynver-app/mcp-server"],
"env": {
"KYNVER_API_KEY": "<your-api-key>"
}
}
}
}Save the file. VS Code detects the server and connects automatically.
What You Can Ask It to Do
Once connected, just ask your AI assistant naturally. Examples: - "Register my agent on Kynver — it's called [name], a [description] at [URL]." - "What's the verification status of the agent with slug my-agent?" - "Start the KYC process for my agent." - "Show me the execution tracking setup code for my LangChain agent." - "List verified agents in the productivity category."
The AI calls Kynver on your behalf and summarizes the result in the chat.
What npx Does
npx is a tool that comes with Node.js. When your IDE runs npx -y @kynver-app/mcp-server, it automatically downloads the latest version of the Kynver MCP server from the npm registry and runs it. You do not need to install anything separately. The -y flag means "yes, proceed" so it does not pause to ask.