MCP

The OpenRegister MCP server gives AI assistants and agents access to company search and data through the Model Context Protocol. It runs remotely, so there is nothing to install.

https://mcp.openregister.de/mcp

When you connect, you enter your API key from OpenRegister Keys.

Connect your assistant

Claude
ChatGPT
Claude Code
Cursor
Other clients

Open OpenRegister in the Claude directory
Click Connect and enter your API key

The connector is then available in Claude on the web, Claude Desktop and the mobile apps.

If you connected OpenRegister in Claude, it already shows up in /mcp.Otherwise, add it and run /mcp to enter your API key:

claude mcp add --transport http openregister https://mcp.openregister.de/mcp

Add this to ~/.cursor/mcp.json and restart Cursor:

{
  "mcpServers": {
    "openregister": {
      "url": "https://mcp.openregister.de/mcp"
    }
  }
}

To skip the sign-in, add "headers": { "Authorization": "Bearer YOUR_API_KEY" } next to url.

Clients that support remote MCP servers take the URL directly. For clients that only run local commands, bridge with mcp-remote (requires Node.js 18+):

{
  "mcpServers": {
    "openregister": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://mcp.openregister.de/mcp"]
    }
  }
}

If the connection fails, clear the auth cache with rm -rf ~/.mcp-auth and try again.

Build with it

In your own agents, send your API key in the Authorization header. The server then skips the OAuth sign-in.

cURL
OpenAI Agents SDK
Vercel AI SDK

curl https://mcp.openregister.de/mcp \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'

from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    async with MCPServerStreamableHttp(
        url="https://mcp.openregister.de/mcp",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
    ) as mcp_server:
        agent = Agent(
            name="company-researcher",
            instructions="Use OpenRegister tools to look up German company data.",
            mcp_servers=[mcp_server],
        )
        result = await Runner.run(agent, "Find information about Trade Republic Bank GmbH")
        print(result.final_output)

import { createOpenAI } from "@ai-sdk/openai";
import { experimental_createMCPClient, generateText } from "ai";

const mcpClient = await experimental_createMCPClient({
  transport: {
    type: "sse",
    url: "https://mcp.openregister.de/sse",
    headers: { Authorization: "Bearer YOUR_API_KEY" },
  },
});

const tools = await mcpClient.tools();

const { text } = await generateText({
  model: createOpenAI({ apiKey: process.env.OPENAI_API_KEY })("gpt-4o"),
  tools,
  prompt: "Find information about Trade Republic Bank GmbH",
});

await mcpClient.close();

https://mcp.openregister.de/sse serves the legacy SSE transport for clients that don’t support Streamable HTTP yet. Prefer /mcp where you can.

Overview

Data Sources

Guides

Integration

Connect your assistant

Build with it

​Connect your assistant

​Build with it

Connect your assistant

Build with it