AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Security & Safety/
redamon
redamon logo

redamon

Active·★ 3.2k·MIT·Updated 2026-10-22
★ Trending

RedAmon is a self-hosted framework for authorized security testing. Its reconnaissance pipeline maps a target's attack surface (subdomains, ports, endpoints, parameters) into a Neo4j knowledge graph that can be queried in natural language, and an agent in a Kali sandbox works through findings with human approval gates on sensitive steps. Projects carry rules of engagement and several hundred per-project settings.

The part that distinguishes it is the remediation side. A triage stage deduplicates and ranks findings, and a code-fix agent can clone a repository, implement changes and open a GitHub pull request for a human to review. The README documents a benchmark result and publishes a self-critical coverage audit that lists which categories are complete, in backlog, or deliberately excluded.

It speaks MCP in both directions: external MCP servers can be added as tools, and an off-by-default MCP server lets an agent such as Claude Code connect in through a token with scoped, re-checked permissions and read-only graph access. Everything runs as Docker Compose services, needing at least 4 GB RAM and 80 GB disk (more with OpenVAS). The project's legal disclaimer restricts use to systems you own or are explicitly authorized to test, and its team is listed under Anthropic's Cyber Verification Program.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-20.

License
MIT
Latest release
v6.14.1 · 2026-09-11
Last commit
2026-10-19
Contributors
24
Forks
670
Open issues and PRs
16
First published
2025-12-29

Source: GitHub, npm and PyPI public APIs.

#penetration-testing#cybersecurity#neo4j#kali-linux#mcp#autonomous-agents#bug-bounty
$ Install
$ git clone https://github.com/samugit83/redamon.git && cd redamon && ./redamon.sh install
↗ Visit site★ GitHub
01

Features

01Parallel multi-tool reconnaissance whose results are merged into a Neo4j attack-surface graph you can query in natural language
02Autonomous exploitation agent running 100+ security tools in a Kali sandbox, with approval gates for dangerous actions
03CypherFix triage and CodeFix agent that dedupe findings, implement fixes and open GitHub pull requests
04Plug in any MCP server as a tool, or connect Claude Code and other agents in through a scoped MCP server with 48 tools
05Multi-user, multi-project tenancy with rules of engagement and 500+ per-project settings
02

Why choose it

+Goes beyond a scan report: findings land in a queryable graph, get triaged, and can turn into a reviewable fix PR.
+Human approval gates and project-level rules of engagement sit in front of sensitive actions.
+MCP in both directions: add external MCP servers as tools, or let your own agent connect in with scoped, read-mostly permissions.
03

Trade-offs

!Heavy to run: many Docker containers, at least 80 GB disk and 4 GB RAM, substantially more for real engagements with OpenVAS.
!Strictly for authorized testing, use on systems without written permission is illegal, so it demands disciplined scoping and oversight.
!A large feature surface and many settings mean meaningful setup and reading before first use.
04

Maintenance check

ActiveChecked: 2026-10-19
Last commit
2026-10-19
Commits, last 90 days
100+
Releases, last 90 days
3
Latest release
v6.14.1 (2026-09-11)
Open issues
15
Recent issues with at least one comment
27/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 51, 88, 69, 25, 19, 72, 101, 53, 132, 172, 46, 41

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #49 Agent Tool Expansion: Shodan, Google Dorking, Python Execution & Memory System1 comments · 2026-03-05
  • #40 Cloud Security Assessment1 comments · 2026-03-05
  • #38 Continuous Attack Surface Monitoring1 comments · 2026-03-05
  • #188 [Feature] Use CamoFox to evade WAFs like Cloudflare0 comments · 2026-09-14
  • #183 [Feature] Potential use of Rubeus and Mimikatz for AD testing0 comments · 2026-09-01

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Claude Code
MCP
Verified via docs
Cursor
MCP
Verified via docs
Codex CLI
MCP
Verified via docs
Docker
Docker Compose
Verified via docs
06

Quick start

1
$ git clone https://github.com/samugit83/redamon.git
2
$ cd redamon
3
$ ./redamon.sh install
07

Use cases

↳Authorized penetration tests and bug bounty work on targets you own or have written permission to test
↳Continuous attack-surface monitoring with findings tracked in a graph
↳Turning confirmed vulnerabilities into reviewed code fixes via pull requests
↳Letting an internal triage agent or CI job query findings over MCP
08

Alternatives

⚡Top VS:
VSARTEX★1.7k→VSnyxstrike★156→VSmcp-virustotal★152→VSmcp-shodan★179→
ARTEX logo
ARTEX★ 1.7k
ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军
VSCompare→
nyxstrike logo
nyxstrike★ 156
AI Powered penetration testing Platform for offensive security research
VSCompare→
mcp-virustotal logo
mcp-virustotal★ 152
MCP server for VirusTotal API — analyze URLs, files, IPs, and domains with comprehensive security reports, relationship analysis, and pagination support.
VSCompare→
mcp-shodan logo
mcp-shodan★ 179
MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Works with Claude Code, Codex, Gemini CLI, and Claude Desktop.
VSCompare→
contrastapi logo
contrastapi★ 35
Security intelligence API and MCP server for AI agents. 25 tools, 35+ endpoints: CVE/EPSS/KEV, domain recon, SSL, IP reputation, threat intel, email security, code scanning. Free, no signup.
VSCompare→
claude-code-pentest logo
claude-code-pentest★ 31
Automate the full pentest process with six Claude Code skills covering recon, exploit chains, and bug bounty report generation from any domain.
VSCompare→
McpVanguard logo
McpVanguard★ 13
An open-source security proxy and active firewall for the Model Context Protocol (MCP). It acts as a real-time 'Reflex System' between AI agents and their tools, protecting the host system from malicious intent, prompt injection, and data exfiltration.
VSCompare→
ida-pro-mcp logo
ida-pro-mcp★ 13.1k
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
samugit83 /
redamon
↗

A self-hosted AI security-testing framework that maps findings into a graph, triages them, and opens fix PRs, with MCP both ways

3.2k670MIT
Last commit1d ago
StatusActive
CategorySecurity & Safety
Contributors24
Latest releasev6.14.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.