Add parameters in static mode

In static mode all parameters (such as Return Types, Required Inputs, etc.) are set as env variables inside the config json. All parameters are either provided as plain strings or as stringified json. See the following example:

{
  "mcpServers": {
    "florentine": {
      "command": "npx",
      "args": ["-y", "@florentine-ai/mcp", "--mode", "dynamic"],
      "env": {
        "FLORENTINE_TOKEN": "<FLORENTINE_API_KEY>",
        "SESSION_ID": "6f7d62f9-8ceb-456b-b7ef-6bd869c3b13a",
        "LLM_SERVICE": "openai",
        "LLM_KEY": "<YOUR_OPENAI_KEY>",
        "RETURN_TYPES": "[\"result\"]",
        "REQUIRED_INPUTS": "[{\"keyPath\":\"accountId\",\"value\":\"507f1f77bcf86cd799439011\"}]"
      }
    }
  }
}

env variables configuration

Variable	Required	Type	Description
FLORENTINE_TOKEN	Yes	String	Your Florentine.ai api key, copy it from dashboard.
SESSION_ID	No	String	The session id of the client. Used for server-side chat history.
LLM_SERVICE	No	String	Specifies the LLM provider to use. Only needed if you did not save the LLM key in your Florentine.ai account.
LLM_KEY	No	String	Your API key for the provided LLM service. Only needed if you did not save the LLM key in your Florentine.ai account.
RETURN_TYPES	No	Stringified JSON	The return types for florentine_ask tool calls.
REQUIRED_INPUTS	No	Stringified JSON	The required inputs. See the required inputs section.