About Aida
Aida is an MCP server published by Vasco0x4 in the Developer Tools category: turn any LLM into an autonomous pentester. You define the scope, the agent does the work, you review the findings.
The repository has 497 stars and 83 forks, with the last commit a month ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/Vasco0x4/AIDAThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
add_card()Log a finding — CVSS 4.0 auto-scored
Parameters not published.
credentials_add()Store credentials, auto-injected via `{{PLACEHOLDER}}`
Parameters not published.
execute()Run any command in the pentesting container
Parameters not published.
http_request()HTTP client with credential auto-substitution
Parameters not published.
python_exec()Execute Python in the container
Parameters not published.
scan()nmap, gobuster, ffuf, nikto, dirb
Parameters not published.
ssl_analysis()TLS/SSL audit
Parameters not published.
subdomain_enum()Subdomain discovery
Parameters not published.
tech_detection()Technology fingerprinting
Parameters not published.
Ask AI
Ask AI about Aida
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository 8 hours ago. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
- ✓Dependencies pinnedA lockfile pins dependency versions.
- !No dynamic code executionSource scan found eval or shell execution. Review how tool inputs reach it before granting credentials.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
Releases
README
AIDA turns any LLM into an autonomous pentester capable of assessing web applications, APIs, and infrastructure. The agent reasons, understands application logic, executes commands in an isolated container, and documents every finding with the commands used.
Real Results
Claude + AIDA isn't just talk. It produces results that end up in CVE databases.
| ID | Severity | Project | Description |
|---|---|---|---|
| CVE-2026-49869 |  |
kestra-io/kestra | Unauthenticated RCE via auth bypass + OS command injection (CWE-78/184/287/918) |
| CVE-2026-50189 / GHSA-xfvv-ggvq-pchh |  |
appsmithorg/appsmith | RCE via newline injection in env variable endpoint |
| CVE-2026-32034 |  |
openclaw/openclaw | Insecure HTTP permits hijacking |
| CVE-2026-49979 / GHSA-vvxf-f8q9-86gh |  |
appsmithorg/appsmith | SSRF via SMTP test endpoint — internal port scanning |
More under responsible disclosure — awaiting publication.
What It Does
AIDA was built to give your AI everything a pentester needs to work.
A fully equipped execution environment. A Docker container loaded with Linux pentesting tools — nmap, sqlmap, ffuf, nuclei, and anything else it needs. If a tool is missing, the agent installs it.
Custom exploitation via Python. The agent generates and executes Python scripts on the fly — custom payloads, encoding tricks, protocol quirks, or any logic that off-the-shelf tools can't handle.
Burp-level HTTP control. The agent sends and manipulates HTTP requests directly — headers, cookies, body, auth tokens. Stored credentials are auto-injected via placeholders. Same power as Burp Repeater, without the UI overhead.
A persistent notebook. The agent logs what it knows about the application, maps attack paths, records observations, flags interesting behaviors, and documents every confirmed vulnerability — commands used, raw output, full context. Stop an engagement and resume it days later for retest, deeper analysis, or handoff.
Where is the real pentester?
You review. The AI hands you findings with full context notes, commands, reproduction steps, and the reasoning that led there. You reproduce, triage, prioritize, and report.
Your expertise stays where it matters. The grunt work runs on its own.
Quick Start
Prerequisites: Docker Desktop + any AI client (Claude, Gemini, GPT...)
git clone https://github.com/Vasco0x4/AIDA.git
cd AIDA
./start.sh
Dashboard: http://localhost:31337
./start.sh --dev— hot reload for contributors./start.sh --lan— share across your local network (HTTPS, self-signed)./start.sh --domain x.com— public deploy with Let's Encrypt./start.sh --localhost— run commands directly on the host (no pentest container) — see Localhost Mode
Launch the Agent
# Launches Claude Code by default
python3 aida.py --assessment "target-corp"
# Auto-detect Claude, Codex, Kimi, or Qwen
python3 aida.py --assessment "target-corp" --cli auto
# Force OpenAI Codex
python3 aida.py --assessment "target-corp" --cli codex
# No confirmation prompts
python3 aida.py --assessment "target-corp" --yes
Define Your Scope
Load assessment 'target-corp' and start the pentest on https://example.com
Scope: all subdomains, authentication flows, API endpoints
Exclude: brute-force on /login
Full setup for all AI clients → INSTALLATION.md
Supported Models
AIDA is model-agnostic. Any LLM with tool-calling support works.
| Client | Setup |
|---|---|
| Claude Code | python3 aida.py (automatic) |
| OpenAI Codex CLI | python3 aida.py --cli codex (automatic) |
| Kimi Code CLI | python3 aida.py (automatic) |
| External API (OpenAI-compatible) | python3 aida.py --base-url |
| Claude Desktop | MCP config |
| ChatGPT Desktop | MCP config |
| Gemini CLI | MCP config |
The smarter the model, the deeper the engagement. Swap models without changing anything else.
Agent Tools
| Tool | |
|---|---|
execute() |
Run any command in the pentesting container |
scan() |
nmap, gobuster, ffuf, nikto, dirb |
subdomain_enum() |
Subdomain discovery |
ssl_analysis() |
TLS/SSL audit |
tech_detection() |
Technology fingerprinting |
python_exec() |
Execute Python in the container |
http_request() |
HTTP client with credential auto-substitution |
add_card() |
Log a finding — CVSS 4.0 auto-scored |
credentials_add() |
Store credentials, auto-injected via {{PLACEHOLDER}} |
Built-in aida-pentest container (~2 GB, starts automatically). Plug in Exegol for 400+ tools — switchable anytime from the dashboard.
Full reference → MCP_TOOLS.md
What's New in v1.1.0
- Authentication — JWT, admin/user roles, first-run setup wizard
- PDF reports — one-click export per assessment
- CVSS 4.0 — automatic scoring on every finding
- Attack timeline — auto-generated per engagement
- Notifications — Telegram, Slack, Email with optional PDF attachment
- Assessment templates — start from predefined methodologies
aida-pentestcontainer — lightweight built-in environment, no Exegol requiredpython_exec+http_request— advanced execution tools- Cross-assessment findings view — aggregate and filter findings across all engagements
- Security hardening — Docker socket proxy, path traversal prevention, localhost-only DB
!! Run locally or on your LAN. Do not expose the dashboard to the public. !!
Documentation
| INSTALLATION.md | Full setup — all AI clients |
| USER_GUIDE.md | Platform usage guide |
| MCP_TOOLS.md | Agent tool reference |
| ARCHITECTURE.md | Technical deep dive |
Contributing
AIDA is actively developed.
Planned:
- OWASP testing guidelines integration
- Multi-agent mode — specialized sub-agents per phase
- Active Directory / internal network module
- Enhanced CLI capabilities
Issues and PRs welcome → GitHub Issues
License
AGPL v3 — free and open source.
Credits
- Anthropic MCP — the tool-calling protocol powering agent actions
- Exegol — supported as alternative container
- The security community for the open-source tooling
README fetched from the repository 8 hours ago. The original is authoritative.