Kali ConnectorSAFE
MCP configuration to connect AI agent to a Linux machine.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP Kali Server (MKS) is a lightweight API bridge that connects MCP clients (e.g: Claude Desktop or 5ire) to the API server which allows executing commands on a Linux terminal.
This MCP is able to run terminal commands as well as interacting with web applications using:
Dirbenum4linuxgobusterHydraJohn the RipperMetasploit-FrameworkNiktoNmapsqlmapWPScan- As well as being able to execute raw commands.
As a result, this is able to perform AI-assisted penetration testing and solving CTF challenges in real time.
Articles Using This Tool
[](https://yousofnahya.medium.com/how-mcp-is-revolutionizing-offensive-security-93b2442a5096)
👉 **How MCP is Revolutionizing Offensive Security**
🔍 Use Case
The goal is to enable AI-driven offensive security testing by:
- Letting the MCP interact with AI endpoints like OpenAI, Claude, DeepSeek, Ollama or any other models.
- Exposing an API to execute commands on a Kali machine.
- Using AI to suggest and run terminal commands to solve CTF challenges or automate recon/exploitation tasks.
- Allowing MCP apps to send custom requests (e.g.
curl,nmap,ffuf, etc.) and receive structured outputs.
Here are some example (using Google's AI gemini 2.0 flash):
Example solving a web CTF challenge from RamadanCTF
https://github.com/user-attachments/assets/dc93b71d-9a4a-4ad5
ceafa1b1b152OBSERVED · 2026-09-27Exposed tools (12)
10 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
dirb_scan | read | |
enum4linux_scan | read | |
execute_command | write | |
gobuster_scan | read | |
hydra_attack | read | |
john_crack | read | |
metasploit_run | write | |
nikto_scan | read | |
nmap_scan | read | |
server_health | read | |
sqlmap_scan | read | |
wpscan_analyze | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
kali-server-mcp --server http://127.0.0.1:5000
./client.py --server http://127.0.0.1:5000
./client.py --server http://127.0.0.1:5000
Flask, requests, mcp
Gates applied: no_behavioural_pass.
ceafa1b1b152full audit observations/trust-audit/mcp-server/wh0am123__kali-connector.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-27 | ceafa1b1b152 | SAFE | B | 89 | first audit |
Questions
What is the Kali Connector MCP server?
MCP configuration to connect AI agent to a Linux machine.
What tools does Kali Connector expose?
12 in total: 10 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Kali Connector safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Kali Connector need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (ceafa1b1b152), read on 2026-09-27. The repository is watched and re-audited when it changes.