InnerVault

Sn1per MCP Server: pentest, recon and attack surface scanning

Stale Official MCP Registry, io.github.1N3

Run scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.

Open the source (opens github.com) https://github.com/1n3/sn1per-mcp

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.

What it is

MCP servers from io.github.1N3.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

pypi package (stdio)

sn1per-mcp@0.9.0

From the server's entry in the official MCP Registry

Settings it asks for

  • SNIPER_MCP_SCOPE · Comma-separated domains, IPs and CIDR ranges you are authorized to test (prefix ! to exclude). Scans outside it are refused.
  • SNIPER_MCP_SCOPE_FILE · Optional absolute path to a scope file with one or more entries per line and # comments.
  • SNIPER_MCP_AUTHORIZATION_REF · Optional authorization reference, such as a statement-of-work or ticket id, recorded in the audit log.
  • SNIPER_MCP_ALLOW_INTRUSIVE · Set to true to offer scan modes that run brute force, exploitation or injection testing. Off by default.
  • SNIPER_MCP_ENABLE_DESTRUCTIVE · Set to true to add the workspace delete and export tools; they ask the human to confirm. Off by default.
  • SNIPER_MCP_REDACT · Redaction of secrets in results. On by default; turn off only with a local model when raw values are required.
  • SNIPER_EDITION · Optional override of the auto-detected Sn1per edition.
  • SNIPER_BIN · Optional absolute path to the sniper CLI. Detected automatically on standard installs.
  • SNIPER_INSTALL_DIR · Optional Sn1per install directory. Read from the CLI or /usr/share/sniper by default.
  • SNIPER_LOOT_BASE · Optional directory that contains the loot workspace tree. Defaults to the install directory's loot folder.
  • SNIPER_SCAN_ENABLED · Set to false for a read-only deployment that never launches scans.

Related

  1. awesome-ai-pentesting

    MCP servers

    A curated list of AI-powered pentesting tools, frameworks, MCP servers, and resources for autonomous cybersecurity operations

    Stale GitHub, skyvanguard 95 ★MITUpdated 22 days ago

    git clone https://github.com/skyvanguard/awesome-ai-pentesting.git
  2. pentest-mcp

    MCP servers

    NOT for educational purposes: An MCP server for professional penetration testers including STDIO/HTTP/SSE support, nmap, go/dirbuster, nikto, JtR, hashcat, wordlist building, and more.

    Stale GitHub, DMontgomery40 150 ★AGPL-3.0Updated 21 days ago

    git clone https://github.com/DMontgomery40/pentest-mcp.git
  3. hexstrike-ai

    MCP servers

    HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

    Stale GitHub, 0x4m4 12.8k ★MITUpdated 3 months ago

    git clone https://github.com/0x4m4/hexstrike-ai.git
  4. MCP-Kali-Server

    MCP servers

    MCP configuration to connect AI agent to a Linux machine.

    Stale GitHub, Wh0am123 847 ★MITUpdated 8 months ago

    git clone https://github.com/Wh0am123/MCP-Kali-Server.git
  5. jadx-ai-mcp

    MCP servers

    Plugin for JADX to integrate MCP server

    Stale GitHub, zinja-coder 2,915 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/zinja-coder/jadx-ai-mcp.git
  6. evil-winrm-py

    MCP servers

    Execute commands interactively on remote Windows machines using the WinRM protocol (just faster)

    Stale GitHub, adityatelange 412 ★MITUpdated 36 days ago

    git clone https://github.com/adityatelange/evil-winrm-py.git