MCP Server

io.github.florentine-ai/mcp MCP Server

Name: io.github.florentine-ai/mcp MCP Server
Author: io.github.florentine-ai

io.github.florentine-ai/mcp

Repository Registry

What is the io.github.florentine-ai/mcp MCP server?

MCP server for Florentine.ai - Natural language to MongoDB aggregations

How to install io.github.florentine-ai/mcp

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

FLORENTINE_TOKEN
required
secret
Your Florentine.ai API key, get it from https://florentine.ai/dashboard
LLM_SERVICE
The LLM service to use, one of 'openai', 'anthropic', 'google' or 'deepseek' (must only be provided if you did not set it in your Florentine.ai account)
LLM_KEY
secret
Your API key for the LLM service (must only be provided if you did not set it in your Florentine.ai account)
SESSION_ID
Session ID for maintaining server-side context across requests
RETURN_TYPES
Stringified JSON array of return types for the response
REQUIRED_INPUTS
Stringified JSON array of values for required inputs keys

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@florentine-ai/mcp",
        "-y",
        "@florentine-ai/mcp@latest",
        "--mode",
        "static",
        "--debug",
        "--logpath"
      ],
      "env": {
        "FLORENTINE_TOKEN": "<YOUR_FLORENTINE_TOKEN>",
        "LLM_SERVICE": "<YOUR_LLM_SERVICE>",
        "LLM_KEY": "<YOUR_LLM_KEY>",
        "SESSION_ID": "<YOUR_SESSION_ID>",
        "RETURN_TYPES": "<YOUR_RETURN_TYPES>",
        "REQUIRED_INPUTS": "<YOUR_REQUIRED_INPUTS>"
      }
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@florentine-ai/mcp",
        "-y",
        "@florentine-ai/mcp@latest",
        "--mode",
        "static",
        "--debug",
        "--logpath"
      ],
      "env": {
        "FLORENTINE_TOKEN": "<YOUR_FLORENTINE_TOKEN>",
        "LLM_SERVICE": "<YOUR_LLM_SERVICE>",
        "LLM_KEY": "<YOUR_LLM_KEY>",
        "SESSION_ID": "<YOUR_SESSION_ID>",
        "RETURN_TYPES": "<YOUR_RETURN_TYPES>",
        "REQUIRED_INPUTS": "<YOUR_REQUIRED_INPUTS>"
      }
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@florentine-ai/mcp",
        "-y",
        "@florentine-ai/mcp@latest",
        "--mode",
        "static",
        "--debug",
        "--logpath"
      ],
      "env": {
        "FLORENTINE_TOKEN": "<YOUR_FLORENTINE_TOKEN>",
        "LLM_SERVICE": "<YOUR_LLM_SERVICE>",
        "LLM_KEY": "<YOUR_LLM_KEY>",
        "SESSION_ID": "<YOUR_SESSION_ID>",
        "RETURN_TYPES": "<YOUR_RETURN_TYPES>",
        "REQUIRED_INPUTS": "<YOUR_REQUIRED_INPUTS>"
      }
    }
  }
}

VS Code

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@florentine-ai/mcp",
        "-y",
        "@florentine-ai/mcp@latest",
        "--mode",
        "static",
        "--debug",
        "--logpath"
      ],
      "env": {
        "FLORENTINE_TOKEN": "<YOUR_FLORENTINE_TOKEN>",
        "LLM_SERVICE": "<YOUR_LLM_SERVICE>",
        "LLM_KEY": "<YOUR_LLM_KEY>",
        "SESSION_ID": "<YOUR_SESSION_ID>",
        "RETURN_TYPES": "<YOUR_RETURN_TYPES>",
        "REQUIRED_INPUTS": "<YOUR_REQUIRED_INPUTS>"
      }
    }
  }
}

Claude Code

claude mcp add mcp --env FLORENTINE_TOKEN=<YOUR_FLORENTINE_TOKEN> --env LLM_SERVICE=<YOUR_LLM_SERVICE> --env LLM_KEY=<YOUR_LLM_KEY> --env SESSION_ID=<YOUR_SESSION_ID> --env RETURN_TYPES=<YOUR_RETURN_TYPES> --env REQUIRED_INPUTS=<YOUR_REQUIRED_INPUTS> -- npx -y @florentine-ai/mcp -y @florentine-ai/mcp@latest --mode static --debug --logpath