Skip to main content
Glama

get_topics

Retrieve available ROS2 topics dynamically to interact with the Unitree Go2 robot via the MCP server, enabling precise control through natural language commands.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • server.py:20-39 (handler)
    The primary MCP tool handler for 'get_topics', decorated with @mcp.tool(). It retrieves ROS2 topics using either WebSocketManager (rosbridge) or direct Ros2Manager based on configuration.
    @mcp.tool()
    def get_topics():
        if use_rosbridge:
            topic_info = ws_manager.get_topics()
            ws_manager.close()
            
            if topic_info:
                topics, types = zip(*topic_info)
                return {
                    "topics": list(topics),
                    "types": list(types)
                }
            else:
                return "No topics found"
        else:
            topics = ros2_manager.get_topics()
            return {
                "topics": topics
            }
  • Helper method in Ros2Manager class that executes shell command to list ROS2 topics directly.
    def get_topics(self) -> list[str]:
        command = f"source {self.setup_sh_path} && ros2 topic list"
        output = subprocess.check_output(command, shell=True, executable='/bin/bash').decode()
        return output.split('\n')
  • Helper method in WebSocketManager class that queries ROS topics via rosbridge WebSocket service.
    def get_topics(self) -> list[tuple[str, str]]:
        self.connect()
        if self.ws:
            try:
                self.send({
                    "op": "call_service",
                    "service": "/rosapi/topics",
                    "id": "get_topics_request_1"
                })
                response = self.receive_binary()
                print(f"[WebSocket] Received response: {response}")
                if response:
                    data = json.loads(response)
                    if "values" in data:
                        topics = data["values"].get("topics", [])
                        types = data["values"].get("types", [])
                        if topics and types and len(topics) == len(types):
                            return list(zip(topics, types))
                        else:
                            print("[WebSocket] Mismatch in topics and types length")
            except json.JSONDecodeError as e:
                print(f"[WebSocket] JSON decode error: {e}")
            except Exception as e:
                print(f"[WebSocket] Error: {e}")
        return []
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

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