Skip to main content
Glama
moimran

EVE-NG MCP Server

by moimran

start_node

Start a stopped node in an EVE-NG network lab to activate network simulation components for testing and configuration.

Instructions

Start a specific node.

This tool starts a node in the lab. The node must be in stopped state to be started successfully.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argumentsYes

Implementation Reference

  • The main handler function for the 'start_node' MCP tool. It validates input using NodeControlArgs, checks EVE-NG connection, delegates to eveng_client.start_node, and formats success/error responses as TextContent.
    @mcp.tool()
    async def start_node(arguments: NodeControlArgs) -> list[TextContent]:
        """
        Start a specific node.
    
        This tool starts a node in the lab. The node must be in stopped state
        to be started successfully.
        """
        try:
            logger.info(f"Starting node {arguments.node_id} in {arguments.lab_path}")
    
            if not eveng_client.is_connected:
                return [TextContent(
                    type="text",
                    text="Not connected to EVE-NG server. Use connect_eveng_server tool first."
                )]
    
            # Start node
            result = await eveng_client.start_node(arguments.lab_path, arguments.node_id)
    
            if result.get('status') == 'success':
                return [TextContent(
                    type="text",
                    text=f"Successfully started node {arguments.node_id} in {arguments.lab_path}\n\n"
                         f"The node is now booting up. It may take a few moments to become fully operational."
                )]
            else:
                return [TextContent(
                    type="text",
                    text=f"Failed to start node: {result.get('message', 'Unknown error')}"
                )]
    
        except Exception as e:
            logger.error(f"Failed to start node: {e}")
            return [TextContent(
                type="text",
                text=f"Failed to start node: {str(e)}"
            )]
  • Pydantic model defining the required input schema (lab_path and node_id) for the start_node tool (shared with stop_node, wipe_node, etc.).
    class NodeControlArgs(BaseModel):
        """Arguments for node control operations."""
        lab_path: str = Field(description="Full path to the lab (e.g., /lab_name.unl)")
        node_id: str = Field(description="Node ID to control")
  • Registration call to register_node_tools (which defines and registers start_node via @mcp.tool() decorator) as part of the main register_tools function.
    # Node management tools
    register_node_tools(mcp, eveng_client)
  • Supporting method in EVENGClientWrapper that ensures connection and calls the underlying EVE-NG SDK API to start the specified node.
    async def start_node(self, lab_path: str, node_id: str) -> Dict[str, Any]:
        """Start a specific node."""
        await self.ensure_connected()
    
        try:
            result = await asyncio.to_thread(self.api.start_node, lab_path, node_id)
            self.logger.info("Started node", lab_path=lab_path, node_id=node_id)
            return result
        except Exception as e:
            self.logger.error("Failed to start node", **log_error(e, {"lab_path": lab_path, "node_id": node_id}))
            raise EVENGAPIError(f"Failed to start node: {str(e)}")
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the prerequisite state ('stopped state') which is useful, but doesn't describe what 'start' entails (e.g., booting a virtual machine, initializing services), potential side effects, error conditions, or response format. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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

Conciseness5/5

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

The description is appropriately sized with two sentences that are front-loaded: the first states the purpose, and the second adds a key constraint. There is no wasted text, and it efficiently communicates essential information without redundancy.

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

Completeness2/5

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

Given the complexity of starting a node (a mutation operation), no annotations, no output schema, and 0% schema description coverage, the description is incomplete. It lacks details on parameters, behavioral outcomes, error handling, and what the tool returns. While concise, it doesn't provide enough context for safe and effective use by an AI agent.

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?

The schema description coverage is 0%, meaning parameters are undocumented in the schema. The description provides no information about parameters, not even mentioning that 'arguments' is required or what it contains (e.g., lab_path and node_id). This fails to compensate for the schema's lack of descriptions, leaving parameters completely unexplained.

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 action ('start') and resource ('a node in the lab'), making the purpose understandable. It distinguishes from siblings like 'stop_node' by specifying the opposite action, but doesn't explicitly differentiate from 'start_all_nodes' which starts multiple nodes. The description is specific but lacks full sibling differentiation.

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

Usage Guidelines3/5

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

The description provides implied usage guidance by stating 'The node must be in stopped state to be started successfully,' which suggests when the tool will work. However, it doesn't explicitly state when to use this vs. alternatives like 'start_all_nodes' or mention prerequisites beyond the node state. The guidance is helpful but incomplete.

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/moimran/eveng-mcp'

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