Lucairn Privacy Gateway
@Declade
Lucairn Privacy Gateway について
Lucairn is an EU-based privacy gateway that sits between your MCP-enabled agent and the upstream LLM (Claude, GPT-4o, o1/o3/o4).
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"lucairn": {
"url": "https://gateway.lucairn.eu/mcp",
"headers": {
"Authorization": "Bearer <YOUR_LUCAIRN_API_KEY>"
}
}
}
}ツール
1Send a chat request through the Lucairn privacy gateway with cross-provider BYOK (Anthropic + OpenAI). PII is detected and replaced with placeholders before reaching the upstream LLM. The gateway picks the upstream provider based on the `model` parameter: `claude-*` / `anthropic-*` use ANTHROPIC_API_KEY; `gpt-*` / `openai-*` / `o1-*` / `o3-*` / `o4-*` use OPENAI_API_KEY. Wire format follows the Anthropic Messages API. Developer-tier responses contain raw placeholders; Pro and Enterprise tiers can enable automatic re-linking back to the original values.
概要
What is Lucairn Privacy Gateway?
Lucairn Privacy Gateway is an EU-based privacy gateway for AI agents. It sits between an MCP-enabled client and upstream OpenAI or Anthropic models, pseudonymizes personally identifiable information (PII) before the model sees it, and returns a signed verification receipt for each request.
How to use Lucairn Privacy Gateway?
Run npx -y @lucairn/mcp-server to start the server. Configure your MCP client (e.g., claude_desktop_config.json) with the command and environment variables LUCAIRN_API_KEY, ANTHROPIC_API_KEY, and/or OPENAI_API_KEY. The server exposes one tool, chat_via_lucairn, which you call with a messages-style payload.
Key features of Lucairn Privacy Gateway
- EU-based privacy gateway for AI agents
- Pseudonymizes PII before the upstream model
- Returns a signed verification receipt per request
- Free Developer tier: 500 requests per month
- Bring your own provider key (BYOK) for OpenAI or Anthropic
- Routes models automatically based on prefix and keys
Use cases of Lucairn Privacy Gateway
- AI agents that must keep user personal data private from model providers
- Customer support assistants that need to anonymize names, emails, and IDs
- Data processing pipelines that require a verifiable privacy layer
FAQ from Lucairn Privacy Gateway
How do I get an API key?
Create a free Developer account at https://lucairn.eu/account/signup.
What models are supported?
The gateway supports any OpenAI or Anthropic model available to your provider account. Model prefixes claude-*/anthropic-* route to Anthropic; gpt-*/openai-*/o1-*/o3-*/o4-* route to OpenAI.
What happens to detected PII?
PII is replaced with placeholders like [PERSON_1] before the request reaches the model. On the Developer tier, placeholders remain visible in responses; Pro and Enterprise tiers support relinking.
Is the Developer tier free?
Yes, the Developer tier includes 500 requests per month and does not require a credit card. You must provide your own OpenAI or Anthropic API key.
Where can I verify a receipt?
Use the verification tool at https://lucairn.eu/verify to check the signed receipt returned with each response.
「AI とエージェント」の他のコンテンツ
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
コメント