Skip to main content
Glama

pub_wirelesscontroller

Control the Unitree Go2 robot via wireless commands by transmitting linear and angular motion parameters, including pitch, yaw, and key inputs, directly to the MCP server for precise execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
durationNo
keysYes
linear_xYes
linear_yYes
pitchYes
yawYes

Implementation Reference

  • server.py:48-57 (handler)
    MCP tool handler for 'pub_wirelesscontroller'. Converts input velocities to normalized stick values (-1 to 1), publishes the WirelessController ROS2 message, and stops after.
    @mcp.tool()
    def pub_wirelesscontroller(linear_x: float, linear_y: float, yaw: float, pitch: float, keys: int, duration: float = 0):
        lx = convert_velocity_to_wirelesscontroller(linear_y)
        ly = convert_velocity_to_wirelesscontroller(linear_x)
        rx = convert_velocity_to_wirelesscontroller(-yaw)
        ry = convert_velocity_to_wirelesscontroller(pitch)
        
        result, msg = wirelesscontroller.publish(lx, ly, rx, ry, keys, duration)
        wirelesscontroller.stop()
        return result
  • Helper function to clamp velocity to [-3.7, 3.7] and normalize to [-1.0, 1.0] for controller sticks.
    def convert_velocity_to_wirelesscontroller(velocity: float):
        if velocity > 3.7:
            velocity = 3.7
        elif velocity < -3.7:
            velocity = -3.7
        # -3.7 ~ 3.7 to -1.0 ~ 1.0
        return velocity / 3.7
  • Class documentation defining the structure and semantics of the WirelessController ROS2 message fields used by the tool.
    class WirelessController:
        """
        Publishes WirelessController messages using ros2 topic pub via subprocess.
        
        Message fields:
          - float32 lx : left stick x axis (-1 ~ 1) -> robot move left and right
          - float32 ly : left stick y axis (-1 ~ 1) -> robot move forward and backward
          - float32 rx : right stick x axis (-1 ~ 1) -> robot rotate left and right
          - float32 ry : right stick y axis (-1 ~ 1) -> robot rotate up and down
          - uint16 keys : button state
        """
  • Core publishing logic: constructs shell command for 'ros2 topic pub' subprocess to send the message with optional rate and duration.
    def publish(self, lx: float, ly: float, rx: float, ry: float, keys: int, duration: float = 0) -> tuple[bool, Any]:
        if self.rate > 0 and duration > 0:
            t = int(self.rate * duration)
            rate_opt = f"-r {self.rate} --times {t}"
        else:
            rate_opt = "-1"
        command = (
            f"source {self.setup_sh_path} && "
            f"ros2 topic pub {self.topic} {self.msg_type} "
            f"'{{lx: {lx}, ly: {ly}, rx: {rx}, ry: {ry}, keys: {keys}}}' {rate_opt}"
        )
        return self.execute(command)
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Related Tools

  • @lpigeon/unitree-go2-mcp-server
  • @lpigeon/unitree-go2-mcp-server
  • @lpigeon/unitree-go2-mcp-server
  • @lpigeon/unitree-go2-mcp-server
  • @lpigeon/unitree-go2-mcp-server
  • @lpigeon/unitree-go2-mcp-server

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/lpigeon/unitree-go2-mcp-server'

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