Skip to content
MCP server

Sn1per MCP Server: pentest, recon and attack surface scanning

Run scoped, audited Sn1per pentest and recon scans from an AI assistant on your own host

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, Linux, self-hosted
Runs
Locally
Version
0.9.0
Listing updated
1 day ago

About Sn1per MCP Server: pentest, recon and attack surface scanning

Sn1per MCP Server: pentest, recon and attack surface scanning is an open-source MCP server for security. It runs locally on your machine and is started by your AI client.

The server sits beside an existing Sn1per installation on a Linux host and runs over stdio. It is not a scanner itself and does not include Sn1per. Its guard rails are the point: scans are refused unless the target falls inside a scope you configure with domains, IPs and CIDR ranges (with exclusions), every scan, cancel, delete and export request is written to a local audit log, and secrets in results are redacted by default.

Intrusive modes that brute force, exploit or test for injection are hidden unless explicitly enabled, and workspace delete and export tools are off by default and ask a human to confirm. A read-only deployment can be set so scans never launch. Results come back as structured findings, open ports, subdomains and technologies.

It supports Sn1per Community Edition 9.x and the 11.x engine of the paid editions, needs Python 3.11 and root or a sudo rule, and is Apache-2.0, beta 0.9. The README restricts use to systems you own or are authorized in writing to test.

Install

Run in a terminal

claude mcp add sn1per-mcp -- uvx sn1per-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "sn1per-mcp": {
      "command": "uvx",
      "args": [
        "sn1per-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "sn1per-mcp": {
      "command": "uvx",
      "args": [
        "sn1per-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "sn1per-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "sn1per-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sn1per-mcp": {
      "command": "uvx",
      "args": [
        "sn1per-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "sn1per-mcp": {
      "command": "uvx",
      "args": [
        "sn1per-mcp"
      ]
    }
  }
}

Configuration

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

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

sniper_status
Reports the Sn1per installation status.
export_workspace
Exports a workspace; opt-in and needs human confirmation.

What it does

Scope enforcement
Refuses targets outside the configured scope.
Audit log
Records scan, cancel, delete and export requests locally.
Structured results
Findings, ports, subdomains and technologies as data.
Secret redaction
Redacts secrets in results by default.
Gated intrusive modes
Brute force and exploitation modes are opt-in.
Read-only option
Disable scan launching entirely.

Good for

  • Start a scoped recon scan from an assistant during an authorized engagement
  • Read open ports and technologies from a finished scan
  • Keep a record of what an agent scanned for a client report
  • Review findings without launching new scans

Pricing

Open source

Apache-2.0; needs a separate Sn1per install

Sn1per MCP Server: pentest, recon and attack surface scanning FAQ

Does it include Sn1per?

No. Sn1per must already be installed on the host.

Which platforms work?

Linux hosts only; macOS and Windows can only act as clients through SSH recipes.

Can it test any target?

No. Scans outside your configured scope are refused, and use is limited to authorized testing.

What licence is it under?

Apache-2.0.

Is Sn1per MCP Server: pentest, recon and attack surface scanning free?

Yes. Sn1per MCP Server: pentest, recon and attack surface scanning is open source, so you can use and self-host it for free.

How do I add Sn1per MCP Server: pentest, recon and attack surface scanning to Claude Code?

Run this command in your terminal: claude mcp add sn1per-mcp -- uvx sn1per-mcp

What are the best alternatives to Sn1per MCP Server: pentest, recon and attack surface scanning?

The closest alternatives to Sn1per MCP Server: pentest, recon and attack surface scanning are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

Alternatives to Sn1per MCP Server: pentest, recon and attack surface scanning

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security