Skip to content

datarobot_genai.drmcp.core.dynamic_tools.deployment.metadata

metadata

get_mcp_tool_metadata 

get_mcp_tool_metadata(deployment: Deployment) -> MetadataBase

Fetch and validate metadata for a given deployment.

This method handles HTTP fetching via request_user_dr_client and delegates pure adapter selection to drmcpbase.build_mcp_tool_metadata.

Parameters:

Name Type Description Default
deployment Deployment

The DataRobot deployment object.

 required
Raises
RuntimeError: If metadata fetching fails.
Returns
MetadataBase adapter instance.
Source code in datarobot_genai/drmcp/core/dynamic_tools/deployment/metadata.py 
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
def get_mcp_tool_metadata(deployment: dr.Deployment) -> MetadataBase:
    """Fetch and validate metadata for a given deployment.

    This method handles HTTP fetching via request_user_dr_client and delegates
    pure adapter selection to drmcpbase.build_mcp_tool_metadata.

    Args:
        deployment: The DataRobot deployment object.

    Raises
    ------
        RuntimeError: If metadata fetching fails.

    Returns
    -------
        MetadataBase adapter instance.
    """
    if _is_datarobot_structured_prediction(deployment):
        return build_mcp_tool_metadata(deployment, None, False)

    info_payload = _fetch_deployment_metadata(deployment)
    supports_chat_api = _fetch_supports_chat_api(deployment)
    return build_mcp_tool_metadata(deployment, info_payload, supports_chat_api)