MCP Servers
26zl/cybersec-toolkit
One command installs 670+ security tools on Linux & Termux.
Our verdict
We have not reviewed 26zl/cybersec-toolkit yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About 26zl/cybersec-toolkit
One command installs more than 670 security tools on Linux and Termux. Its authorization-gated MCP server works with Claude Code, OpenCode, Codex, Gemini CLI, Ollama-backed agents, and other MCP clients. It includes over 870 agent skills for CTF, pentesting, bug bounty, DFIR, and red or blue team work, acting as a companion by default and switching to autonomous mode when asked.
Best for
Security practitioners on Linux or Termux who want an AI agent ready with a broad offensive and defensive toolset
Use cases
- Stand up a full security toolchain on a fresh Linux or Termux environment
- Give an MCP-compatible coding agent access to pentesting and DFIR tooling
- Attach a red or blue team skill library to an AI agent for CTF or bug bounty work
Notes
56 stars on GitHub. Last updated 2026-09-15. Licensed MIT.
Pros
- Extremely broad tool and skill coverage in a single install
- Works across many popular agent runtimes via MCP
- Authorization gate gives agents safe default behavior
Cons
- Small community with only 56 stars, so limited peer validation
- No single vendor backing, which may affect long-term maintenance
- Autonomous mode carries inherent risk if used on unauthorized systems
Key facts
What we have checked
- Days since the last commit
- 4
- GitHub forks
- 18
- GitHub stars
- 92
- Days to a first reply on issues
- 58.2
- Open issues
- 1
- Releases in the last 90 days
- 5
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
How to use
How to set it up
As the listing publishes it. We have not run this install.
Install
git clone --depth 1 --branch v1.4.0 https://github.com/26zl/cybersec-toolkit.git && cd cybersec-toolkit && sudo ./install.sh --profile ctfTools exposed
list_toolscheck_installedget_tool_infoget_module_infoget_profile_toolssuggest_for_ctfsuggest_for_bountyguided_assessmentget_cve_inforecommend_installlist_profilesrun_toolrun_pipelinerun_scriptmanage_remote_hosts
Clients the listing names (not checked here)
Claude Desktop, Claude Code, Cursor, Cline, Continue, VS Code
Install
Add 26zl/cybersec-toolkit to your client
Our lab has not run this server yet. "Config checked" on a client means the recipe matches that client's documented config format; it does not mean we ran it.
Claude Code
Config checkedRun in your terminal (runs on your computer)
claude mcp add --transport stdio 26zl-cybersec-toolkit -- docker run -i --rm --entrypoint uv --security-opt no-new-privileges ghcr.io/26zl/cybersec-toolkit:1.4.0 run --directory mcp_server fastmcp run server.py --transport stdio --no-bannerClaude Desktop
Config checkedAdd to claude_desktop_config.json (runs on your computer)
{
"mcpServers": {
"26zl-cybersec-toolkit": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--entrypoint",
"uv",
"--security-opt",
"no-new-privileges",
"ghcr.io/26zl/cybersec-toolkit:1.4.0",
"run",
"--directory",
"mcp_server",
"fastmcp",
"run",
"server.py",
"--transport",
"stdio",
"--no-banner"
]
}
}
}Cursor
Config checkedAdd to .cursor/mcp.json (runs on your computer)
{
"mcpServers": {
"26zl-cybersec-toolkit": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--entrypoint",
"uv",
"--security-opt",
"no-new-privileges",
"ghcr.io/26zl/cybersec-toolkit:1.4.0",
"run",
"--directory",
"mcp_server",
"fastmcp",
"run",
"server.py",
"--transport",
"stdio",
"--no-banner"
]
}
}
}VS Code
Config checkedAdd to .vscode/mcp.json (runs on your computer)
{
"servers": {
"26zl-cybersec-toolkit": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--entrypoint",
"uv",
"--security-opt",
"no-new-privileges",
"ghcr.io/26zl/cybersec-toolkit:1.4.0",
"run",
"--directory",
"mcp_server",
"fastmcp",
"run",
"server.py",
"--transport",
"stdio",
"--no-banner"
]
}
}
}Codex
Config checkedAdd to ~/.codex/config.toml (runs on your computer)
[mcp_servers.26zl-cybersec-toolkit]
command = "docker"
args = ["run", "-i", "--rm", "--entrypoint", "uv", "--security-opt", "no-new-privileges", "ghcr.io/26zl/cybersec-toolkit:1.4.0", "run", "--directory", "mcp_server", "fastmcp", "run", "server.py", "--transport", "stdio", "--no-banner"]- ChatGPT: ChatGPT connects only to remote servers that need no API key.
Recipes come from the server's entry in the official MCP registry. Check the package name before you run it, and keep keys out of shared files.
Works with
What 26zl/cybersec-toolkit connects to
5 clients, each with how we know and when we checked.
| Works with | Type | How we know | Checked |
|---|---|---|---|
| Claude Code | Client | Install recipe matches the client's documented formatRuns locally, version 1.4.0Config checked | Claude Code docs |
| Claude Desktop | Client | Install recipe matches the client's documented formatRuns locally, version 1.4.0Config checked | Claude Desktop docs |
| Cursor | Client | Install recipe matches the client's documented formatRuns locally, version 1.4.0Config checked | Cursor docs |
| VS Code | Client | Install recipe matches the client's documented formatRuns locally, version 1.4.0Config checked | VS Code docs |
| Codex | Client | Install recipe matches the client's documented formatRuns locally, version 1.4.0Config checked | Codex docs |
Stars and usage
How 26zl/cybersec-toolkit is growing
84 to 92
Health and security
Is 26zl/cybersec-toolkit looked after, and what do its setup files show
Health score
45 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 30 of 30 | Last push 4 days ago |
| Releases | 15 of 15 | 5 releases in 90 days |
| Issue replies | 0 of 20 | First reply in 58.2 days (median) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | 0 of 20 | Community server |
Security check static checks
100 out of 100
- Note No published npm or PyPI package of this repository was found, so package advisories were not checked.
- Note The lab has not recorded this server's tool list yet, so tool permissions were not checked.
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
LaurieWired/GhidraMCP
Various
MCP Server for Ghidra
mrexodia/ida-pro-mcp
Various
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
semgrep/semgrep
Various
Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.
skill-seekers/Skill_Seekers
Various
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.