Sliverc2

MCP Server for Sliver C2

python

2

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "d4vydm-sliverc2_mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "sliverc2_mcp",
        "run",
        "sliverc2_mcp.py",
        "--operator-config-file",
        "sliver_operator.cfg"
      ]
    }
  }
}

You run a Sliver MCP Server for the Sliver C2 framework to expose controllable, scripted actions via the MCP protocol. This server is implemented in Python and is designed to work with a Sliver operator configuration, enabling you to perform management tasks, execute commands, and inspect system state through a unified MCP interface.

How to use

Start the MCP server to connect your Sliver C2 operator to the MCP interface. You will use an MCP client to issue commands such as listing active beacons, querying sessions, uploading and downloading files, executing commands, and reading or dumping data from target processes. Begin by launching the server with your operator configuration, then connect your MCP client to issue the available tool actions.

How to install

Prerequisites you need to have installed on the host where you run the MCP server:

Python 3.10 or newer
uv (the MCP runner)
sliver-py (Python client for Sliver) version 0.0.19 or newer
mcp[cli] version 1.2.0 or newer

Install and run steps

Ensure Python is installed and accessible as python3.
Install the required Python packages.

python3 -m pip install --upgrade sliver-py>=0.0.19 mcp[cli]>=1.2.0

Prepare your Sliver operator configuration file (sliver_operator.cfg) with the appropriate mTLS credentials and Sliver server details.
Run the MCP server using the provided command from the configuration snippet.

"uv": {
  "command": "/Users/<user>/.local/bin/uv",
  "args": [
    "--directory",
    "sliverc2_mcp",
    "run",
    "sliverc2_mcp.py",
    "--operator-config-file",
    "sliver_operator.cfg"
  ]
}

To start the server you will generally run

Capture the final start command from your configuration and execute it to bring the MCP server online.

Available tools

list_beacons

Lists all beacons currently connected to the Sliver C2 server, showing beacon IDs, user hosts, and last check-in times.

list_sessions

Retrieves active Sliver sessions, including session IDs, user contexts, and associated beacons.

change_directory

Changes the working directory context for subsequent commands within the MCP session.

list_files

Lists files within a target directory or the current working directory of a beacon.

upload_file

Uploads a file from your local machine to a destination path on the target system.

download_file

Downloads a file from the target system to your local machine.

run_cmd_command

Executes a command in the target environment and returns stdout, stderr, and exit status.

run_ps_command

Runs a PowerShell command on the target and returns the output.

run_shellcode

Executes raw shellcode on the target if supported by Sliver integration.

list_processes

Lists running processes on the target, including PID, name, and user.

impersonate

Performs user impersonation on the target where permitted by the agent.

run_as

Runs a command under a different user context on the target system.

read_registry_value

Reads a Windows registry value from the remote target.

dump_process_memory

Dumps the memory of a specified process for offline analysis.