Skip to main content
Glama
sandraschi

Robotics MCP Server

robotics_system

Manage robotics systems by getting help documentation, checking server status, or listing registered robots with filtering options.

Instructions

System management portmanteau for Robotics MCP.

PORTMANTEAU PATTERN RATIONALE: Instead of creating 3 separate tools (help, status, list_robots), this tool consolidates related system operations into a single interface. This design:

  • Prevents tool explosion (3 tools → 1 tool) while maintaining full functionality

  • Improves discoverability by grouping related operations together

  • Reduces cognitive load when working with system management tasks

  • Enables consistent system interface across all operations

  • Follows FastMCP 2.13+ best practices for feature-rich MCP servers

SUPPORTED OPERATIONS:

  • help: Get comprehensive help information about the server and its tools

  • status: Get server status with connectivity tests and robot counts

  • list_robots: List all registered robots with optional filtering

Args: operation: The system operation to perform. MUST be one of: - "help": Get help information (no additional parameters) - "status": Get server status (no additional parameters) - "list_robots": List robots (optional: robot_type, is_virtual filters)

robot_type: Optional filter for list_robots operation.
    Valid values: "scout", "go2", "g1", or any custom robot type.
    If None, returns all robot types.

is_virtual: Optional filter for list_robots operation.
    - True: Only virtual robots (vbots)
    - False: Only physical robots (bots)
    - None: Both virtual and physical robots

Returns: Dictionary containing operation-specific results: - help: Server info, tool list, features, mounted servers - status: Server health, robot counts, connectivity tests, HTTP status - list_robots: Robot list with filtering applied

Examples: Get help information: result = await robotics_system(operation="help")

Get server status:
    result = await robotics_system(operation="status")

List all robots:
    result = await robotics_system(operation="list_robots")

List only Scout robots:
    result = await robotics_system(operation="list_robots", robot_type="scout")

List only virtual robots:
    result = await robotics_system(operation="list_robots", is_virtual=True)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYes
robot_typeNo
is_virtualNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Core handler function for the 'robotics_system' tool. Dispatches to specific handlers based on 'operation' parameter (help, status, list_robots). Includes input schema via type hints and comprehensive docstring.
    @self.mcp.tool()
    async def robotics_system(
        operation: Literal["help", "status", "list_robots"],
        robot_type: Optional[str] = None,
        is_virtual: Optional[bool] = None,
    ) -> Dict[str, Any]:
        """System management portmanteau for Robotics MCP.
    
        PORTMANTEAU PATTERN RATIONALE:
        Instead of creating 3 separate tools (help, status, list_robots), this tool
        consolidates related system operations into a single interface. This design:
        - Prevents tool explosion (3 tools → 1 tool) while maintaining full functionality
        - Improves discoverability by grouping related operations together
        - Reduces cognitive load when working with system management tasks
        - Enables consistent system interface across all operations
        - Follows FastMCP 2.13+ best practices for feature-rich MCP servers
    
        SUPPORTED OPERATIONS:
        - help: Get comprehensive help information about the server and its tools
        - status: Get server status with connectivity tests and robot counts
        - list_robots: List all registered robots with optional filtering
    
        Args:
            operation: The system operation to perform. MUST be one of:
                - "help": Get help information (no additional parameters)
                - "status": Get server status (no additional parameters)
                - "list_robots": List robots (optional: robot_type, is_virtual filters)
    
            robot_type: Optional filter for list_robots operation.
                Valid values: "scout", "go2", "g1", or any custom robot type.
                If None, returns all robot types.
    
            is_virtual: Optional filter for list_robots operation.
                - True: Only virtual robots (vbots)
                - False: Only physical robots (bots)
                - None: Both virtual and physical robots
    
        Returns:
            Dictionary containing operation-specific results:
            - help: Server info, tool list, features, mounted servers
            - status: Server health, robot counts, connectivity tests, HTTP status
            - list_robots: Robot list with filtering applied
    
        Examples:
            Get help information:
                result = await robotics_system(operation="help")
    
            Get server status:
                result = await robotics_system(operation="status")
    
            List all robots:
                result = await robotics_system(operation="list_robots")
    
            List only Scout robots:
                result = await robotics_system(operation="list_robots", robot_type="scout")
    
            List only virtual robots:
                result = await robotics_system(operation="list_robots", is_virtual=True)
        """
        try:
            if operation == "help":
                return await self._handle_help()
            elif operation == "status":
                return await self._handle_status()
            elif operation == "list_robots":
                return await self._handle_list_robots(robot_type, is_virtual)
            else:
                return format_error_response(
                    f"Unknown operation: {operation}",
                    error_type="validation_error",
                    operation=operation,
                )
        except Exception as e:
            return handle_tool_error("robotics_system", e, operation=operation)
  • Registration of the robotics_system tool by calling the register() method on the instantiated RoboticsSystemTool.
    self.robotics_system.register()  # System: help, status, list_robots
    logger.debug("Registered robotics_system tool")
  • Import of RoboticsSystemTool class and instantiation with required dependencies (MCP server, state_manager, config, etc.).
    from robotics_mcp.tools.robotics_system import RoboticsSystemTool
    from robotics_mcp.tools.robot_behavior import RobotBehaviorTool
    from robotics_mcp.tools.robot_virtual import RobotVirtualTool
    from robotics_mcp.tools.workflow_management import WorkflowManagementTool
    
    # Consolidated portmanteau tools (SOTA: max 15 tools)
    # Note: RobotControlTool and RobotModelTools are imported at module level
    self.robotics_system = RoboticsSystemTool(
        self.mcp, self.state_manager, self.config, self.config_loader, self.mounted_servers
    )
  • Helper method implementing the 'help' operation, providing server info, tools list, features, and configuration.
    async def _handle_help(self) -> Dict[str, Any]:
        """Handle help operation."""
        try:
            # Get all registered tools
            tools_info = []
            # FastMCP stores tools in _tools dict - get description from docstring
            for tool_name, tool_func in getattr(self.mcp, '_tools', {}).items():
                description = ""
                if hasattr(tool_func, '__doc__') and tool_func.__doc__:
                    # Get first line of docstring as description
                    description = tool_func.__doc__.split('\n')[0].strip()
                tools_info.append(
                    {
                        "name": tool_name,
                        "description": description,
                    }
                )
    
            return format_success_response(
                "Help information retrieved",
                data={
                    "server_name": "Robotics-MCP",
                    "version": "0.1.0",
                    "description": (
                        "Unified robotics control via MCP - Physical and virtual robots (bot + vbot). "
                        "Provides comprehensive control for Moorebot Scout, Unitree robots, and virtual "
                        "robots in Unity/VRChat. Integrates with osc-mcp, unity3d-mcp, vrchat-mcp, and "
                        "avatar-mcp for seamless virtual robotics testing."
                    ),
                    "features": [
                        "Physical robot control (ROS 1.4 via rosbridge)",
                        "Virtual robot control (Unity3D/VRChat/Resonite)",
                        "YDLIDAR SuperLight (95g) LiDAR integration",
                        "World Labs Marble/Chisel environment generation",
                        "Multi-robot coordination",
                        "Dual transport (stdio + HTTP)",
                    ],
                    "tools": tools_info,
                    "mounted_servers": list(self.mounted_servers.keys()),
                    "configuration": {
                        "http_enabled": self.config.enable_http,
                        "http_port": self.config.http_port if self.config.enable_http else None,
                        "config_path": str(self.config_loader.config_path),
                    },
                },
            )
        except Exception as e:
            logger.error("Failed to generate help", error=str(e), exc_info=True)
            return format_error_response("Failed to generate help information", details={"error": str(e)})
  • Helper method implementing the 'status' operation, including robot counts, mounted servers status, and HTTP connectivity.
    async def _handle_status(self) -> Dict[str, Any]:
        """Handle status operation."""
        try:
            robots = self.state_manager.list_robots()
    
            # Test mounted server connectivity
            mounted_servers_status: Dict[str, Any] = {}
            for server_name, server_instance in self.mounted_servers.items():
                try:
                    if hasattr(server_instance, "list_tools"):
                        tools = server_instance.list_tools()
                        mounted_servers_status[server_name] = {
                            "available": True,
                            "tools_count": len(tools) if isinstance(tools, dict) else 0,
                        }
                    else:
                        mounted_servers_status[server_name] = {
                            "available": True,
                            "tools_count": "unknown",
                        }
                except Exception as e:
                    logger.warning("Mounted server connectivity test failed", server=server_name, error=str(e))
                    mounted_servers_status[server_name] = {
                        "available": False,
                        "error": str(e),
                    }
    
            # Test HTTP server if enabled
            http_status = None
            if self.config.enable_http:
                try:
                    import socket
    
                    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
                    sock.settimeout(1)
                    result = sock.connect_ex((self.config.http_host, self.config.http_port))
                    sock.close()
                    http_status = {
                        "enabled": True,
                        "host": self.config.http_host,
                        "port": self.config.http_port,
                        "reachable": result == 0,
                    }
                except Exception as e:
                    logger.warning("HTTP server status check failed", error=str(e))
                    http_status = {
                        "enabled": True,
                        "host": self.config.http_host,
                        "port": self.config.http_port,
                        "reachable": False,
                        "error": str(e),
                    }
    
            return format_success_response(
                "Server status retrieved successfully",
                data={
                    "version": "0.1.0",
                    "status": "healthy",
                    "robots": [r.to_dict() for r in robots],
                    "robots_count": len(robots),
                    "mounted_servers": mounted_servers_status,
                    "http": http_status,
                    "config": {
                        "http_enabled": self.config.enable_http,
                        "log_level": self.config.log_level,
                    },
                },
            )
        except Exception as e:
            return handle_tool_error("robotics_system", e, operation="status")
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does this well. It clearly explains the three supported operations, what each returns, and provides multiple examples of usage. The description discloses that this is a read-only system management interface (help, status, listing) without any destructive operations mentioned. It could be improved by mentioning rate limits or authentication requirements.

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

Conciseness3/5

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

The description is appropriately front-loaded with the purpose and rationale, but includes extensive implementation rationale that may not be essential for tool selection. The 'PORTMANTEAU PATTERN RATIONALE' section explains design decisions rather than focusing purely on usage. While well-structured with clear sections, it could be more concise by focusing only on information needed for tool invocation.

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

Completeness5/5

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

Given the complexity of a multi-operation tool with 3 parameters and no annotations, the description is remarkably complete. It explains all operations, parameters, return values, and provides multiple examples. With an output schema present, the description appropriately focuses on explaining what each operation returns rather than detailing the exact return structure. This provides sufficient context for an agent to understand and use the tool effectively.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by providing comprehensive parameter documentation. It explains the 'operation' parameter with its three valid values, details the optional 'robot_type' filter with valid values and behavior, and explains the 'is_virtual' filter with its three possible states. The description adds significant value beyond the bare schema by explaining parameter semantics, defaults, and usage context.

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

Purpose3/5

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

The description states this is a 'system management portmanteau' that consolidates help, status, and list_robots operations, which provides a vague but accurate purpose. However, it doesn't clearly distinguish this from sibling tools like robot_behavior or robot_control, and the term 'portmanteau' may be confusing to some agents. The description explains what it does but could be more specific about the exact functionality.

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

Usage Guidelines4/5

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

The description provides clear context about when to use this tool by explaining it consolidates three related system operations and listing the specific operations supported. It mentions this follows best practices for preventing tool explosion and grouping related operations, which gives good guidance. However, it doesn't explicitly state when NOT to use it or provide alternatives among the sibling tools.

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/sandraschi/robotics-mcp'

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