Skip to main content
Glama
wagonbomb

Megaraptor MCP

by wagonbomb

quarantine_client

Isolate or restore network access for a Velociraptor client to maintain communication with the server during incident response.

Instructions

Quarantine or unquarantine a Velociraptor client.

Quarantining a client isolates it from the network while maintaining communication with the Velociraptor server.

Args: client_id: The client ID (e.g., 'C.1234567890abcdef') quarantine: True to quarantine, False to unquarantine (default: True) message: Optional message to include with the quarantine action

Returns: Quarantine status of the client.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
client_idYes
quarantineNo
messageNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The main handler for the quarantine_client tool, decorated with @mcp.tool() for registration.
    @mcp.tool()
    async def quarantine_client(
        client_id: str,
        quarantine: bool = True,
        message: Optional[str] = None,
    ) -> list[TextContent]:
        """Quarantine or unquarantine a Velociraptor client.
    
        Quarantining a client isolates it from the network while maintaining
        communication with the Velociraptor server.
    
        Args:
            client_id: The client ID (e.g., 'C.1234567890abcdef')
            quarantine: True to quarantine, False to unquarantine (default: True)
            message: Optional message to include with the quarantine action
    
        Returns:
            Quarantine status of the client.
        """
        try:
            # Validate client_id
            client_id = validate_client_id(client_id)
    
            client = get_client()
    
            if quarantine:
                # Quarantine the client using the Windows.Remediation.Quarantine artifact
                # or appropriate artifact for the client's OS
                vql = f"""
                SELECT collect_client(
                    client_id='{client_id}',
                    artifacts='Windows.Remediation.Quarantine',
                    env=dict(MessageBox='{message or "System quarantined by administrator"}')
                ) FROM scope()
                """
            else:
                # Unquarantine
                vql = f"""
                SELECT collect_client(
                    client_id='{client_id}',
                    artifacts='Windows.Remediation.Quarantine',
                    env=dict(RemovePolicy='Y')
                ) FROM scope()
                """
    
            results = client.query(vql)
    
            return [TextContent(
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 and successfully discloses key behavioral traits: network isolation mechanics, reversibility (supports unquarantine), and the ability to attach messages. Missing safety/permission details prevents a 5.

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

Conciseness4/5

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

The docstring format with Args/Returns sections is slightly verbose but highly readable. Information is front-loaded with the action summary and effect explanation before parameter details, with no wasted sentences.

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?

For a 3-parameter tool with an output schema present, the description is complete: it covers functionality, behavioral effects, all parameters with examples, and acknowledges the return value without redundant elaboration.

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?

Despite 0% schema description coverage, the Args section comprehensively documents all three parameters: client_id includes a concrete example format, quarantine explains the boolean logic and default value, and message clarifies its optional nature and purpose.

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 opens with a specific verb pair ('Quarantine or unquarantine') and clear resource ('Velociraptor client'), immediately distinguishing it from sibling tools like label_client or get_client_info which handle different client operations.

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 explains what quarantining does ('isolates it from the network while maintaining communication with the Velociraptor server'), which implies usage context, but lacks explicit when-to-use guidance or contrasts with alternatives like label_client.

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/wagonbomb/megaraptor-mcp'

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