Skip to main content
Glama
CW-Codewalnut

Metabase MCP Server

get_dashboard_cards

Retrieve all cards from a specific Metabase dashboard to analyze or manage its visualizations and data components.

Instructions

Get cards in a dashboard.

Args: dashboard_id (int): ID of the dashboard.

Returns: Dict[str, Any]: Cards in the dashboard.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dashboard_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The main handler function for the get_dashboard_cards tool. It accepts a dashboard_id parameter and returns cards from the specified dashboard by making a GET request to the Metabase API endpoint /api/dashboard/{dashboard_id}/cards. The function is decorated with @mcp.tool() which registers it as an MCP tool.
    @mcp.tool()
    async def get_dashboard_cards(dashboard_id: int) -> Dict[str, Any]:
        """
        Get cards in a dashboard.
    
        Args:
            dashboard_id (int): ID of the dashboard.
    
        Returns:
            Dict[str, Any]: Cards in the dashboard.
        """
        logger.info(f"Getting cards for dashboard {dashboard_id}")
        return await make_metabase_request(RequestMethod.GET, f"/api/dashboard/{dashboard_id}/cards")
  • Initialization of the FastMCP server instance named 'mcp'. This is the MCP server object that the @mcp.tool() decorator uses to register the get_dashboard_cards function as an available tool.
    mcp = FastMCP("metabase", lifespan=app_lifespan)
  • The make_metabase_request helper function that handles all HTTP communication with the Metabase API. It accepts RequestMethod, endpoint, and optional parameters, then makes the actual API call. The get_dashboard_cards handler delegates to this function with RequestMethod.GET and the appropriate endpoint.
    async def make_metabase_request(
        method: RequestMethod,
        endpoint: str,
        data: Optional[Dict[str, Any] | bytes] = None,
        params: Optional[Dict[str, Any]] = None,
        json: Any = None,
        headers: Optional[Dict[str, str]] = None,
    ) -> Dict[str, Any]:
        """
        Make a request to the Metabase API.
        
        Args:
            method: HTTP method to use (GET, POST, PUT, DELETE)
            endpoint: API endpoint path
            data: Request data (for form data)
            params: URL parameters
            json: JSON request body
            headers: Additional headers
            
        Returns:
            Dict[str, Any]: Response data
            
        Raises:
            MetabaseConnectionError: When the Metabase server is unreachable
            MetabaseResponseError: When Metabase returns a non-2xx status code
            RuntimeError: For other errors
        """
        
        if not METABASE_URL or not METABASE_API_KEY:
            raise RuntimeError("METABASE_URL or METABASE_API_KEY environment variable is not set. Metabase API requests will fail.")
    
        if session is None:
            raise RuntimeError("HTTP session is not initialized. Ensure app_lifespan was called.")
    
        try:
            request_headers = headers or {}
            
            logger.debug(f"Making {method.name} request to {METABASE_URL}{endpoint}")
            
            # Log request payload for debugging (omit sensitive info)
            if json and logger.level <= logging.DEBUG:
                sanitized_json = {**json}
                if 'password' in sanitized_json:
                    sanitized_json['password'] = '********'
                logger.debug(f"Request payload: {sanitized_json}")
                
            response = await session.request(
                method=method.name,
                url=endpoint,
                timeout=aiohttp.ClientTimeout(total=30),
                headers=request_headers,
                data=data,
                params=params,
                json=json,
            )
    
            try:
                # Handle 500 errors with more detailed info
                if response.status >= 500:
                    error_text = await response.text()
                    logger.error(f"Server error {response.status}: {error_text[:200]}")
                    raise MetabaseResponseError(response.status, f"Server Error: {error_text[:200]}", endpoint)
                
                response.raise_for_status()
                response_data = await response.json()
                
                # Ensure the response is a dictionary for FastMCP compatibility
                return ensure_dict_response(response_data)
                
            except aiohttp.ContentTypeError:
                # Handle empty responses or non-JSON responses
                content = await response.text()
                if not content:
                    return {"data": {}}
                logger.warning(f"Received non-JSON response: {content}")
                return {"data": content}
    
        except aiohttp.ClientConnectionError as e:
            logger.error(f"Connection error: {str(e)}")
  • The RequestMethod enum defines the HTTP methods (GET, POST, PUT, DELETE) used by the helper function. The get_dashboard_cards tool uses RequestMethod.GET to specify the HTTP method for the API request.
    class RequestMethod(Enum):
        GET = auto()
        POST = auto()
        PUT = auto()
        DELETE = auto()
  • The DashboardCard dataclass defines the schema for a dashboard card in Metabase. While not directly used by the get_dashboard_cards function (which returns Dict[str, Any]), this model represents the structure of cards that may be returned and is used by related dashboard manipulation tools.
    @dataclass
    class DashboardCard:
        """
        Represents a card within a Metabase dashboard.
        
        Attributes:
            id (int): Use negative numbers to auto generate the ids 
                or use any unique value but,
                it must be unique within the dashboard
            card_id (int): The ID of the card/visualization
            row (int): The row position in the dashboard grid
            col (int): The column position in the dashboard grid
            size_x (int): The width of the card in grid units
            size_y (int): The height of the card in grid units
            parameter_mappings (List[Dict[str, Any]]): Parameter mappings for the card
        """
        id: int  # Use negative numbers to auto generate the ids
        card_id: int
        row: int
        col: int
        size_x: int
        size_y: int
        parameter_mappings: List[Dict[str, Any]] = field(default_factory=list)
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'Get cards in a dashboard,' which implies a read-only operation, but doesn't clarify aspects like authentication requirements, rate limits, error handling, or what 'cards' entail (e.g., metadata, content, or both). This leaves significant gaps for safe and effective use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and concise, with a clear purpose statement followed by separate 'Args' and 'Returns' sections. Every sentence serves a purpose without redundancy, making it easy to parse and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (1 parameter) and the presence of an output schema (implied by 'Returns: Dict[str, Any]'), the description is somewhat complete. However, with no annotations and minimal behavioral details, it falls short of providing full context for reliable use, especially compared to sibling tools that might offer similar functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description includes an 'Args' section that explains the 'dashboard_id' parameter as 'ID of the dashboard,' adding semantic meaning beyond the schema's title 'Dashboard Id' and type 'integer.' Since schema description coverage is 0%, this compensates partially, but it's minimal and doesn't elaborate on format or constraints (e.g., valid ranges).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get cards in a dashboard.' This specifies the verb ('Get') and resource ('cards in a dashboard'), making it easy to understand what the tool does. However, it doesn't explicitly distinguish this from sibling tools like 'get_dashboard_items' or 'get_metabase_cards', which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With sibling tools such as 'get_dashboard_items' and 'get_metabase_cards' available, there's no indication of how this tool differs in context, scope, or use cases, leaving the agent to guess based on names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CW-Codewalnut/metabase-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server