amihacked
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Why
An agent can reason about an intrusion, but it cannot see one. Left to run shell commands on its own, it produces a different investigation every time, and nothing stops it from stating things it never checked.
amihacked fixes both:
It gives the agent eyes. Fixed collectors turn a machine or a file into structured evidence records, each with an ID and a hash.
It keeps the agent honest. Findings, from the built-in rules or from the agent itself, are rejected unless they cite records that exist.
It needs no lab. One install, read-only, runs entirely on your machine.
Works with Claude Code, Codex, Cursor, Gemini CLI, or anything else that speaks MCP.
Related MCP server: HexWitness
Quick start
Needs Node.js 20 or newer. amihacked is not on npm yet, so build it from source:
git clone https://github.com/ekupekuAI/amihacked.gitcd amihacked && npm install && npm run buildTry it on the bundled examples, no agent needed:
node dist/cli.js file examples/auth.log examples/access.logInspect this computer (Windows):
node dist/cli.js scan --report case.mdAdd it to Claude Code, using the full path to your clone:
claude mcp add amihacked -- node /path/to/amihacked/dist/cli.js mcpThen ask:
Am I hacked? Check this computer and show me the evidence.For other agents, register the same command as a stdio MCP server.
How it works
Collect. Collectors and readers turn the system into evidence records. They are fixed scripts and parsers; the agent cannot change what they run.
Detect. Rules read the evidence and raise findings, each with a severity, a confidence, a MITRE ATT&CK technique and the most likely innocent explanation.
Investigate. The agent searches the evidence, follows the timeline, and records its own conclusions. A conclusion that cites no real evidence ID is refused.
Report. One verdict, the findings with their evidence, and a plain list of what could not be checked.
What it looks at
The live machine (Windows)
Area | What is collected |
Startup | Run keys, Winlogon values, Startup folders |
Scheduled tasks | Tasks outside |
Services | Every service and the file it launches |
Processes | Path, command line, parent, publisher signature |
Network | Listening ports and open connections, with the owning program |
Antivirus | Defender state and recorded detections |
Accounts | Local users and administrators |
Hosts file | Address overrides |
Event logs | Failed and remote logons, new accounts, cleared logs, installed services, flagged PowerShell |
Evidence files (any OS unless noted)
File | What is extracted |
pcap / pcapng | Flows, DNS lookups, TLS server names, HTTP requests, unencrypted logins, regular "check-in" traffic, DNS tunnelling |
SSH auth log | Login attempts per address, password guessing, a success right after many failures |
Web access log | Requests carrying SQL injection, path traversal, command injection, Log4Shell and scanner signatures |
Windows | The same security events as the live scan (needs Windows in this version) |
The file type is detected from the content, not the name.
What you get
A verdict, one of three: no signs of compromise in what was checked, suspicious items need a closer look, or strong signs of compromise. The strongest verdict needs strong evidence, not a pile of weak signals.
Findings with a severity, a confidence, a MITRE ATT&CK technique, the most likely innocent explanation, and the evidence IDs behind them.
Coverage: what was checked and, just as plainly, what could not be.
A Markdown report you can keep or hand to someone else.
MCP tools
Tool | Purpose |
| Inspect the machine the server runs on |
| Read an evidence file into the case |
| Examine the collected records |
| Records in time order, optionally around a moment |
| Record the agent's own conclusion; refused without real evidence IDs |
| Markdown report with verdict, findings, evidence and coverage |
| Start over |
Safety
Read-only. It never changes, deletes or quarantines anything.
Local. It makes no network connections and uploads nothing.
No agent-supplied commands. Collectors are fixed scripts. Values from the agent travel as data and are never spliced into a script.
Evidence is treated as hostile. Text from logs and captures is cleaned and capped, and a rule flags content written to steer an AI ("ignore previous instructions...").
Passwords are redacted. A login seen in a capture is recorded by username only.
Limits
A clear verdict means nothing was found in the areas listed under Coverage. It does not prove a system is clean. Kernel rootkits, firmware implants and malware that hides from the operating system are out of reach.
It is not an antivirus and gives no real-time protection.
Without administrator rights the Windows Security log cannot be read, so logon and account events are missing. The report says so when that happens.
Rules are heuristics. Each finding states its confidence and an innocent explanation; read both before acting.
Live scanning of macOS and Linux, cross-platform
.evtx, disk images and memory dumps are not supported yet.
Roadmap
Live collectors for macOS and Linux
Pure TypeScript
.evtxand registry-hive parsers, so evidence files work on any OSBrowser-extension and WMI persistence collectors
An npm release, so
npx amihackedworksKnown-answer cases that grade an agent's conclusions
Development
npm installnpm testThe design is in docs/DESIGN.md. Issues and pull requests are welcome, especially new detection rules with a test and an innocent explanation.
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Read-only evidence reports on AI agents: search, fetch a report, check trust. Not a certification.
Read-only discovery for AgentCheck, a visitor-side security review of AI chatbots and agents.
Read-only finance and operations controls for AI agents with evidence and safe next actions.
Read-only release evidence for coding agents: findings, deliveries, source and runtime data.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform digital forensics analysis including memory analysis, file metadata inspection, and threat-intelligence lookups.8 npmISC
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query persistent, build-scoped evidence memory for reverse engineering, combining static analysis, runtime captures, and claims with honest uncertainty. Provides read-only access to an evidence graph and MCP prompts for structured investigations.99 npm2Apache 2.0
- AlicenseBqualityCmaintenanceEnables MCP-compatible agents to perform read-only incident investigations by querying logs, building timelines, searching runbooks, validating evidence, and creating ticket drafts only with explicit approval.7MIT
- AlicenseCqualityBmaintenanceEnables AI agents to inspect forensic disk images locally and read-only across file systems, registry hives, event logs, databases, prefetch, shortcuts, and unallocated space. Every result includes supporting evidence and limitations, with timeline and search operations available through MCP tools.35MIT