Skip to main content
Glama
CW-Codewalnut

Metabase MCP Server

get_metabase_cards

Retrieve all saved questions and their metadata from Metabase to access BI insights and manage analytics assets.

Instructions

Get a list of all saved questions (cards).

Returns: Dict[str, Any]: Cards metadata including names, ids, collections.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The handler function that implements the get_metabase_cards tool. It retrieves all saved questions (cards) from Metabase by making a GET request to the /api/card endpoint. The function is async, takes no parameters, and returns a dictionary containing card metadata including names, IDs, and collections.
    @mcp.tool()
    async def get_metabase_cards() -> Dict[str, Any]:
        """
        Get a list of all saved questions (cards).
    
        Returns:
            Dict[str, Any]: Cards metadata including names, ids, collections.
        """
        logger.info("Getting all cards")
        return await make_metabase_request(RequestMethod.GET, "/api/card")
  • The @mcp.tool() decorator registers the get_metabase_cards function as an MCP tool with the FastMCP framework. This decorator is what makes the function available as a tool in the MCP server.
    @mcp.tool()
  • Helper function that handles all HTTP requests to the Metabase API. It manages the aiohttp session, handles authentication via API key, implements error handling for connection and response errors, and ensures responses are in dictionary format for FastMCP compatibility. This is used by get_metabase_cards to make the actual API call.
    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)}")
            raise MetabaseConnectionError("Metabase is unreachable. Is the Metabase server running?") from e
        except aiohttp.ClientResponseError as e:
            logger.error(f"Response error: {e.status}, {e.message}, {e.request_info.url}")
            raise MetabaseResponseError(e.status, e.message, str(e.request_info.url)) from e
        except Exception as e:
            logger.error(f"Request error: {str(e)}")
            raise RuntimeError(f"Request error: {str(e)}") from e
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the action ('Get a list') and return type, but lacks details on permissions, rate limits, pagination, or error handling. For a tool with no annotations, this leaves significant behavioral gaps, though it doesn't contradict any annotations.

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

Conciseness4/5

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

The description is brief and front-loaded with the core purpose in the first sentence. The second sentence adds return value details, which is useful given the output schema. There's no wasted text, though it could be slightly more structured for clarity.

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 simplicity (0 parameters, output schema exists), the description is adequate but minimal. It covers the basic purpose and return type, but lacks context on usage, behavior, or sibling differentiation. With no annotations and an output schema, it meets minimum viability but has clear gaps in guidance and transparency.

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

Parameters4/5

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add param info, which is appropriate here. A baseline of 4 is applied as per rules for 0 parameters, since it doesn't need to compensate for any schema gaps.

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 verb ('Get') and resource ('list of all saved questions (cards)'), making the purpose evident. It distinguishes from siblings like 'get_card_query_results' by focusing on metadata retrieval rather than query execution. However, it doesn't explicitly differentiate from other 'get' tools like 'get_metabase_collection' or 'get_metabase_dashboards' beyond the resource name.

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?

No guidance is provided on when to use this tool versus alternatives. With siblings like 'get_metabase_collection' and 'get_metabase_dashboards', the description lacks context on whether this is for general listing, filtering, or specific use cases. It mentions returning metadata but doesn't specify prerequisites or exclusions.

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