Skip to main content
Glama
moimran

EVE-NG MCP Server

by moimran

wipe_all_nodes

Reset all nodes in an EVE-NG lab to factory state by deleting user configurations and rebuilding from images.

Instructions

Wipe all nodes in a lab (reset to factory state).

This tool wipes all nodes in the lab, deleting all user configuration including startup-configs, VLANs, and other settings. The next start will rebuild all nodes from their selected images.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argumentsYes

Implementation Reference

  • MCP tool handler for wipe_all_nodes: validates input, checks EVE-NG connection, calls client.wipe_all_nodes, formats success/error response.
    @mcp.tool()
    async def wipe_all_nodes(arguments: BulkNodeControlArgs) -> list[TextContent]:
        """
        Wipe all nodes in a lab (reset to factory state).
    
        This tool wipes all nodes in the lab, deleting all user configuration
        including startup-configs, VLANs, and other settings. The next start
        will rebuild all nodes from their selected images.
        """
        try:
            logger.info(f"Wiping all nodes 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."
                )]
    
            # Wipe all nodes
            result = await eveng_client.wipe_all_nodes(arguments.lab_path)
    
            if result.get('status') == 'success':
                return [TextContent(
                    type="text",
                    text=f"Successfully wiped all nodes in {arguments.lab_path}\n\n"
                         f"⚠️  All user configurations have been deleted. All nodes have been reset to factory state.\n"
                         f"The next start will rebuild all nodes from their selected images."
                )]
            else:
                return [TextContent(
                    type="text",
                    text=f"Failed to wipe all nodes: {result.get('message', 'Unknown error')}"
                )]
    
        except Exception as e:
            logger.error(f"Failed to wipe all nodes: {e}")
            return [TextContent(
                type="text",
                text=f"Failed to wipe all nodes: {str(e)}"
            )]
  • Pydantic schema defining the input arguments for wipe_all_nodes (lab_path). Shared with other bulk operations.
    class BulkNodeControlArgs(BaseModel):
        """Arguments for bulk node operations."""
        lab_path: str = Field(description="Full path to the lab (e.g., /lab_name.unl)")
  • Registration call for node management tools (including wipe_all_nodes) within the central register_tools function.
    # Node management tools
    register_node_tools(mcp, eveng_client)
  • Core client wrapper method that performs the wipe_all_nodes operation by calling the EVE-NG API.
    async def wipe_all_nodes(self, lab_path: str) -> Dict[str, Any]:
        """Wipe all nodes in a lab (reset to factory state)."""
        await self.ensure_connected()
    
        try:
            result = await asyncio.to_thread(self.api.wipe_all_nodes, lab_path)
            self.logger.info("Wiped all nodes", lab_path=lab_path)
            return result
        except Exception as e:
            self.logger.error("Failed to wipe all nodes", **log_error(e, {"lab_path": lab_path}))
            raise EVENGAPIError(f"Failed to wipe all nodes: {str(e)}")
  • Top-level call to register all tools (including wipe_all_nodes) in the MCP server initialization.
    register_tools(self.mcp, self.eveng_client)
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. It effectively describes the destructive nature ('deleting all user configuration'), scope ('all nodes'), and outcome ('rebuild all nodes from their selected images'). It doesn't cover aspects like permissions, rate limits, or error handling, but provides solid core behavioral information.

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 front-loaded with the core purpose in the first sentence, followed by specific details in the second. Both sentences earn their place by adding value—no wasted words or redundancy. The structure is clear and efficient.

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 tool's complexity (destructive operation with no annotations and no output schema), the description is moderately complete. It covers the action, scope, and outcome well but lacks details on parameters, error conditions, or what 'factory state' entails. For a high-stakes tool, more context would be beneficial.

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?

The schema description coverage is 0%, with one parameter ('lab_path') undocumented in the schema. The description doesn't mention parameters at all, failing to compensate for the schema gap. However, since there's only one parameter, the baseline is 4, but the lack of any parameter guidance in the description reduces it to 3.

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

Purpose5/5

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

The description clearly states the specific action ('wipe all nodes in a lab'), the resource ('nodes in a lab'), and distinguishes it from the sibling tool 'wipe_node' by specifying it affects 'all nodes' rather than individual nodes. The phrase 'reset to factory state' further clarifies the outcome.

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 implies usage context by stating it deletes 'all user configuration' and rebuilds nodes 'from their selected images,' suggesting it's for resetting a lab. However, it doesn't explicitly state when to use this versus alternatives like 'delete_lab' or 'wipe_node,' nor does it mention prerequisites like lab existence or permissions.

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