Florentine.ai 模型上下文协议（MCP）服务器允许您将 MongoDB 和 MySQL 数据的自然语言查询**直接集成到自定义的 AI 代理或 AI 桌面应用中。

问题由AI代理转发到MCP服务器，转化为数据库查询，查询结果返回给代理进行进一步处理。

此外，它还有一些额外功能，例如：

• 多租户使用的安全数据隔离
• 自动化模式探索
• 语义向量搜索/RAG支持，并自动嵌入创建
• **高级查找支持 **
• 排除密钥

注： 如果你在寻找我们的API，可以在这里找到。

目录

• 先决条件
• 安装
• 可用工具
• 论证
• 认证
• 连接你的大型语言模型账户
• 选项1：将LLM密钥保存在您的账户中（推荐）
• 选项2：在MCP服务器配置env变量中提供你的LLM密钥
• 积分模式
• 静态模式
• 环境变量
• 动态模式
• 示例分解
• florentine_ask参数
• 返回类型
• 提供返回类型
• 返回类型配置

Florentine.ai MCP Server - Talk to your MongoDB & MySQL data

The Florentine.ai Model Context Protocol (MCP) Server lets you integrate natural language querying for your MongoDB & MySQL data directly into your custom AI Agent or AI Desktop App.

Questions are forwarded by the AI Agent to the MCP Server, transformed into database queries and the query results are returned to the agent for further processing.

Also has a couple of extra features under the hood, e.g.:

• Secure data separation for multi-tenant usage
• Automated schema exploration
• Semantic vector search/RAG support with automated embedding creation
• Advanced lookup support
• Exclusion of keys

Note: If you are looking for our API you can find it here.

Contents

• Prerequisites
• Installation
• Available Tools
• Arguments
• Authentication
• Connect your LLM account
  • Option 1: Save your LLM key in your account (recommended)
  • Option 2: Provide your LLM key inside the MCP server config env variables
• Integration Modes
  • Static Mode
    • Environment variables
  • Dynamic Mode
    • Example breakdown
    • florentine_ask Parameters
• Return Types
  • Providing Return Types
  • Return Types Configuration
• Secure Data Separation for multi-tenant usage
  • Providing Required Inputs
  • Required Inputs Configuration
  • Supported Value Types
  • Usage Examples
• Sessions
  • Providing a session
• Errors
  • Custom client error handling
  • Common Errors

Prerequisites

• Node.js >= v18.0.0
• A Florentine.ai account (create a free account here)
• A connected database and at least one analyzed and activated collection/table in your Florentine.ai account
• A Florentine.ai API Key (you can find yours on your account dashboard)

Installation

A detailed documentation of the MCP Server can be found here in our docs.

You can easily run the server using npx. See the following example for Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "florentine": {
      "command": "npx",
      "args": ["-y", "@florentine-ai/mcp", "--mode", "static"],