Skip to main content
Glama

getDevice

Retrieve a Meraki device's details using its serial number. Query device configuration and status directly.

Instructions

Get device by serial

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
serialYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The MCP tool handler for 'getDevice' - an async function decorated with @mcp.tool() that takes a serial parameter and delegates to call_meraki_method('devices', 'getDevice', serial=serial)
    async def getDevice(serial: str) -> str:
        """Get device by serial"""
        return await call_meraki_method("devices", "getDevice", serial=serial)
  • The @mcp.tool() decorator that registers the getDevice function as an MCP tool
    @mcp.tool()
  • The call_meraki_method helper that wraps the synchronous Meraki SDK call in an async wrapper via to_async and _call_meraki_method_internal
    async def call_meraki_method(section: str, method: str, **params) -> str:
        """Internal async wrapper for pre-registered tools"""
        return await to_async(_call_meraki_method_internal)(section, method, params)
  • The _call_meraki_method_internal function that actually invokes dashboard.devices.getDevice() via the Meraki SDK, with caching, pagination enforcement, error handling, and response size management
    def _call_meraki_method_internal(section: str, method: str, params: dict) -> str:
        """Internal helper to call Meraki API methods"""
        pagination_limited = False
        original_params = params.copy()
    
        try:
            # Validate section
            if not hasattr(dashboard, section):
                return json.dumps({
                    "error": f"Invalid section '{section}'",
                    "available_sections": SDK_SECTIONS
                }, indent=2)
    
            section_obj = getattr(dashboard, section)
    
            # Validate method
            if not hasattr(section_obj, method):
                return json.dumps({
                    "error": f"Method '{method}' not found in section '{section}'"
                }, indent=2)
    
            method_func = getattr(section_obj, method)
    
            if not callable(method_func):
                return json.dumps({"error": f"'{method}' is not callable"}, indent=2)
    
            # Determine operation type
            is_read = is_read_only_operation(method)
            is_write = is_write_operation(method)
    
            # Read-only mode check
            if READ_ONLY_MODE and is_write:
                return json.dumps({
                    "error": "Write operation blocked - READ_ONLY_MODE is enabled",
                    "method": method,
                    "hint": "Set READ_ONLY_MODE=false in .env to enable"
                }, indent=2)
    
            # Auto-fill org ID if needed
            sig = inspect.signature(method_func)
            method_params = [p for p in sig.parameters.keys() if p != 'self']
    
            if 'organizationId' in method_params and 'organizationId' not in params and MERAKI_ORG_ID:
                params['organizationId'] = MERAKI_ORG_ID
    
            # Enforce pagination limits
            params_before = params.copy()
            params = enforce_pagination_limits(params, method)
            if params != params_before:
                pagination_limited = True
    
            # Check cache for read operations
            if ENABLE_CACHING and is_read:
                cache_key = create_cache_key(section, method, params)
                cached = cache.get(cache_key)
                if cached is not None:
                    if isinstance(cached, dict):
                        cached['_from_cache'] = True
                    return json.dumps(cached, indent=2)
    
            # Call the method
            result = method_func(**params)
    
            # Invalidate cached read results for this section after any write operation
            if ENABLE_CACHING and is_write:
                cache.invalidate(section)
    
            # Check response size and handle large responses
            result_json = json.dumps(result)
            estimated_tokens = estimate_token_count(result_json)
    
            if ENABLE_FILE_CACHING and estimated_tokens > MAX_RESPONSE_TOKENS:
                # Save full response to file
                filepath = save_response_to_file(result, section, method, original_params)
    
                # Create truncated response with metadata
                truncated_response = create_truncated_response(result, filepath, section, method, original_params)
    
                # Add pagination warning if limits were enforced
                if pagination_limited:
                    truncated_response["_pagination_limited"] = True
                    truncated_response["_pagination_message"] = f"Request modified: pagination limited to {MAX_PER_PAGE} items per page"
    
                # Cache the truncated response (not the full result)
                if ENABLE_CACHING and is_read:
                    cache_key = create_cache_key(section, method, params)
                    cache.set(cache_key, truncated_response)
    
                return json.dumps(truncated_response, indent=2)
    
            # Normal response (small enough)
            response_data = result
            if pagination_limited and isinstance(response_data, dict):
                response_data["_pagination_limited"] = True
                response_data["_pagination_message"] = f"Request modified: pagination limited to {MAX_PER_PAGE} items per page"
    
            # Cache read results
            if ENABLE_CACHING and is_read:
                cache_key = create_cache_key(section, method, params)
                cache.set(cache_key, response_data)
    
            return json.dumps(response_data, indent=2)
    
        except meraki.exceptions.APIError as e:
            return json.dumps({
                "error": "Meraki API Error",
                "message": str(e),
                "status": getattr(e, 'status', 'unknown')
            }, indent=2)
        except TypeError as e:
            return json.dumps({
                "error": "Invalid parameters",
                "message": str(e),
                "hint": f"Use get_method_info(section='{section}', method='{method}') for parameter details"
            }, indent=2)
        except Exception as e:
            return json.dumps({
                "error": str(e),
                "type": type(e).__name__
            }, indent=2)
  • The list of pre-registered tool names reported in get_mcp_config, including 'getDevice'
    "pre_registered_tools": ["getOrganizations", "getOrganizationAdmins", "getOrganizationNetworks",
                              "getOrganizationDevices", "getNetwork", "getNetworkClients",
                              "getNetworkEvents", "getNetworkDevices", "getDevice",
                              "getNetworkWirelessSsids", "getDeviceSwitchPorts", "updateDeviceSwitchPort"],
Behavior2/5

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

No annotations are provided, and the description is minimal. It implies a read operation but omits details such as data freshness, authentication requirements, rate limits, or side effects. The description carries the burden but fails to disclose these traits.

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 a single, front-loaded sentence of five words. It is concise and earns its place, though it omits optional context.

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 existence of an output schema, the description does not need to explain return values. However, it is very terse and could add context about conditions (e.g., device not found). Adequate for a simple retrieval tool but not rich.

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?

Schema description coverage is 0%, so the description must compensate. It identifies the serial parameter role ('by serial') but adds no constraints or format details. The value is marginal beyond the schema.

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 'Get device by serial' clearly states the action (get) and resource (device) along with the key identifier (serial). It distinguishes from siblings like getNetwork or getNetworkDevices, but could be more specific about the type of device or scope.

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 like getNetworkDevices or getOrganizationDevices. The description lacks context for selection.

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/CiscoDevNet/meraki-magic-mcp-community'

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