mcp · florentine-ai — Claude Code MCP server: what it does, how to install
An MCP server that translates natural language prompts into MongoDB aggregations and MySQL queries directly inside your agent workflow.
claude mcp add --env FLORENTINE_TOKEN=<FLORENTINE_TOKEN> --env LLM_SERVICE=<LLM_SERVICE> --env LLM_KEY=<LLM_KEY> --env SESSION_ID=<SESSION_ID> --env RETURN_TYPES=<RETURN_TYPES> --transport stdio florentine-ai-mcp -- npx -y @florentine-ai/mcpWhat mcp does
This server connects coding assistants to MongoDB and MySQL instances via Florentine.ai. When you ask questions in conversational English, it maps intent into database queries and returns records or calculations back to your chat. The package exposes two core MCP tools: florentine_list_collections to inspect accessible collections with field types, and florentine_ask to execute queries.
The architecture includes multi-tenant data separation and key exclusion to hide sensitive fields. Setup requires Node.js 18.0.0 or newer, a FLORENTINE_TOKEN credential, and an LLM API key from OpenAI, Google, Anthropic, or Deepseek. Configuration operates via --mode static for standard desktop clients or --mode dynamic for custom integrations. Without at least one activated collection in your Florentine dashboard, queries will fail immediately.
What it helps with
- Query MongoDB and MySQL collections using conversational prompts
- Inspect active database schemas and column types via florentine_list_collections
- Enforce tenant isolation across multi-tenant database environments
- Mask sensitive keys from database query responses
Example prompts for the agent
- Run
florentine_list_collectionsto inspect active database collections and their schema types - Use
florentine_askto calculate total revenue per customer category in MongoDB - Ask
florentine_askto fetch recent signups with pending verification from MySQL
How to install mcp
Platform CLI
claude mcp add --env FLORENTINE_TOKEN=<FLORENTINE_TOKEN> --env LLM_SERVICE=<LLM_SERVICE> --env LLM_KEY=<LLM_KEY> --env SESSION_ID=<SESSION_ID> --env RETURN_TYPES=<RETURN_TYPES> --transport stdio florentine-ai-mcp -- npx -y @florentine-ai/mcpReplace <…> with your own values. 1 more environment variable is in the server README
Platform CLI
codex mcp add florentine-ai-mcp --env FLORENTINE_TOKEN=<FLORENTINE_TOKEN> --env LLM_SERVICE=<LLM_SERVICE> --env LLM_KEY=<LLM_KEY> --env SESSION_ID=<SESSION_ID> --env RETURN_TYPES=<RETURN_TYPES> -- npx -y @florentine-ai/mcpReplace <…> with your own values. 1 more environment variable is in the server README
Config file
{
"mcpServers": {
"florentine-ai-mcp": {
"command": "npx",
"args": [
"-y",
"@florentine-ai/mcp"
],
"env": {
"FLORENTINE_TOKEN": "<FLORENTINE_TOKEN>",
"LLM_SERVICE": "<LLM_SERVICE>",
"LLM_KEY": "<LLM_KEY>",
"SESSION_ID": "<SESSION_ID>",
"RETURN_TYPES": "<RETURN_TYPES>"
}
}
}
}Replace <…> with your own values. 1 more environment variable is in the server README
Config file
{
"servers": {
"florentine-ai-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@florentine-ai/mcp"
],
"env": {
"FLORENTINE_TOKEN": "<FLORENTINE_TOKEN>",
"LLM_SERVICE": "<LLM_SERVICE>",
"LLM_KEY": "<LLM_KEY>",
"SESSION_ID": "<SESSION_ID>",
"RETURN_TYPES": "<RETURN_TYPES>"
}
}
}
}Replace <…> with your own values. 1 more environment variable is in the server README
Platform CLI
gemini mcp add -e FLORENTINE_TOKEN=<FLORENTINE_TOKEN> -e LLM_SERVICE=<LLM_SERVICE> -e LLM_KEY=<LLM_KEY> -e SESSION_ID=<SESSION_ID> -e RETURN_TYPES=<RETURN_TYPES> florentine-ai-mcp npx -y @florentine-ai/mcpReplace <…> with your own values. 1 more environment variable is in the server README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about mcp
How to install mcp in Claude Code?
Run `claude mcp add --env FLORENTINE_TOKEN=<FLORENTINE_TOKEN> --env LLM_SERVICE=<LLM_SERVICE> --env LLM_KEY=<LLM_KEY> --env SESSION_ID=<SESSION_ID> --env RETURN_TYPES=<RETURN_TYPES> --transport stdio florentine-ai-mcp -- npx -y @florentine-ai/mcp. You can also run the minimal command: claude mcp add mcp -e FLORENTINE_TOKEN=<FLORENTINE_TOKEN> -e LLM_KEY=<LLM_KEY> -- npx -y @florentine-ai/mcp`.
What does this MCP server do?
It forwards conversational questions to the Florentine.ai engine, generates database queries for MongoDB or MySQL, and passes the output to the AI assistant.
Which LLM providers are supported?
The server uses a bring-your-own-key model supporting OpenAI, Google, Anthropic, and Deepseek via the LLM_SERVICE parameter.
Similar MCP servers
All MCP servers for Data and databases →mcp by other authors comes first.
