MCP-Kali-Server
MCP configuration to connect AI agent to a Linux machine.
No outside reports on file
This tool gives an AI agent direct control over a Linux machine, so only use it in isolated testing environments with accounts that have minimal permissions and no access to real production systems or sensitive data.
Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionRuns shell or system commandsREVIEW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (Wh0am123/MCP-Kali-Server)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/Wh0am123/MCP-Kali-Server ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-24.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About MCP-Kali-Server
This is a connector that lets AI agents send commands to and run scripts on a Linux machine (specifically one running Kali Linux, a penetration-testing operating system). The AI can execute shell commands, read files, and interact with the system through this bridge.
Who it’s for
Security researchers, penetration testers, and developers who want to automate testing tasks on a Linux machine using an AI agent. It's intended for technical users in controlled environments.
Alternatives
- OpenAI Code Interpreter (cloud-based Python code execution, less direct system access)
- Anthropic Tools API (integrate custom tools without full shell access)
- E2B Sandbox (isolated, temporary Linux environments for AI agents)
- LocalAI with system integration (locally-hosted AI with optional scripting; more control over permissions)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/Wh0am123/MCP-Kali-Server (opens external site) for installation and configuration steps, as setup varies by your Claude or AI platform version.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 865
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Full system access: The AI gains permission to run any shell command the connected Linux user account can run, potentially reading sensitive files, deleting data, or installing malware.
- Credential exposure: If the connection isn't encrypted or authenticated, passwords, API keys, or SSH credentials stored on the Linux machine could be intercepted or stolen.
- Prompt injection: An attacker could embed hidden commands in files or web pages that trick the AI into running harmful scripts (like deleting files or stealing data).
- Unaudited code execution: The project's code isn't formally audited; bugs could allow unintended command execution or privilege escalation.
- Network exposure: If the server is exposed to the internet without strong authentication, anyone could potentially connect and control the machine.
How to lower the risk
Least-privilege permissions
- Run the connector as a non-root user with no access to sensitive files or system config.
- Use OS-level user restrictions to limit what the AI account can execute.
Network isolation
- Keep the Linux machine disconnected from the internet or behind a strict firewall.
- Use a VPN or isolated network if remote access is needed; never expose the server publicly.
Monitoring
- Log all commands the AI sends and all files it accesses; review logs regularly.
- Set up alerts for unusual activity like attempts to access /etc/shadow or system binaries.
Red flags to watch for
- The AI suddenly asking to read config files, /etc/, or .ssh directories.
- Commands that modify system permissions, install packages, or create new user accounts.
- Requests to connect to external networks or download files from the internet.
Questions
How do I install MCP-Kali-Server?
MCP-Kali-Server does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Wh0am123/MCP-Kali-Server.
Are there security reports about MCP-Kali-Server?
No reports found for this package in our research (last checked 2026-10-30). MCP-Kali-Server currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include full system access, credential exposure, prompt injection.
Is MCP-Kali-Server actively maintained?
MCP-Kali-Server has 865 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Wh0am123/MCP-Kali-Server before pinning it in production.
What are alternatives to MCP-Kali-Server?
Notable alternatives to MCP-Kali-Server include OpenAI Code Interpreter, Anthropic Tools API, E2B Sandbox, LocalAI with system integration. You can also compare MCP-Kali-Server side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use MCP-Kali-Server? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/wh0am123-mcp-kali-server)HTML embed:
<a href="https://agentarmorhq.com/skills/wh0am123-mcp-kali-server"><img src="https://agentarmorhq.com/api/badge/wh0am123-mcp-kali-server" alt="AgentArmorHQ Risk Grade for MCP-Kali-Server" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "wh0am123-mcp-kali-server"Share with your security lead
Need sign-off to use MCP-Kali-Server? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: MCP-Kali-Server
- **Listing URL:** https://agentarmorhq.com/skills/wh0am123-mcp-kali-server
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 865 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** Runs shell or system commands
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (Wh0am123/MCP-Kali-Server)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Wh0am123/MCP-Kali-Server
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- Wh0am123
- Source code
- github.com/Wh0am123/MCP-Kali-Server
- Est. context load
- ~1k tokens / turn (~6 tool schemas, 0.5% of 200k context)
- Popularity
- 865 GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-24
Community
Discussions for MCP-Kali-Server
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude