io.github.florentine-ai/mcp

io.github.florentine-ai/mcp·v0.2.1·Databases

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

Trust verdict · v1 advisory · method

NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables

FLORENTINE_TOKEN

requiredsecret

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

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Databases

ai.haymon/dbmcp

Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite with PII redaction and write-prevention

ai.smithery/MisterSandFR-supabase-mcp-selfhosted

Manage Supabase projects end to end across database, auth, storage, realtime, and migrations. Moni…

ai.smithery/afgong-sqlite-mcp-server

Explore your Messages SQLite database to browse tables and inspect schemas with ease. Run flexible…

Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@florentine-ai/mcp"
      ],
      "env": {
        "FLORENTINE_TOKEN": "<your-florentine_token>",
        "LLM_SERVICE": "<llm_service>",
        "LLM_KEY": "<your-llm_key>",
        "SESSION_ID": "<session_id>",
        "RETURN_TYPES": "<return_types>",
        "REQUIRED_INPUTS": "<required_inputs>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@florentine-ai/mcp"
      ],
      "env": {
        "FLORENTINE_TOKEN": "<your-florentine_token>",
        "LLM_SERVICE": "<llm_service>",
        "LLM_KEY": "<your-llm_key>",
        "SESSION_ID": "<session_id>",
        "RETURN_TYPES": "<return_types>",
        "REQUIRED_INPUTS": "<required_inputs>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y @florentine-ai/mcp

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-florentine-ai-mcp

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.2.1
category: Databases
quality: 63 / 100
operator: florentine-ai

Provenance

Verdict history is anchored to Bitcoin via OpenTimestamps. The free tier returns the current verdict only; the anchored record is served on the authenticated tier.

Links

Repository →