autopentest-ai

AutoPentest is an agentic pentesting MCP server for web applications. It orchestrates multiple role-specialized agents (Scout/Analyzer/Exploiter/Reporter) across a structured multi-phase workflow that crawls and maps an application, then performs OWASP WSTG-aligned testing and PortSwigger technique-based exploitation attempts, producing evidence-backed reports and doing quality-gated verification. It also bundles security tooling in Docker and includes browser-based testing via a Playwright MCP component (per README).

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Security security pentesting web-application-testing mcp owasp portswigger owasp-wstg daST agentic-ai
⚙ Agent Friendliness
50
/ 100
Can an agent use this?
🔒 Security
30
/ 100
Is it safe for agents?
⚡ Reliability
34
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
55
Error Messages
0
Auth Simplicity
60
Rate Limits
25

🔒 Security

TLS Enforcement
20
Auth Strength
20
Scope Granularity
40
Dep. Hygiene
45
Secret Handling
30

Security considerations are mixed: the tool is intended for offensive testing and bundles many scanners/exploit tools. The provided README excerpt does not document network transport/security controls (TLS requirements) for the MCP server, secret handling practices, or authentication/authorization for connecting agents to the MCP server. It does describe some safety-related controls at the workflow level (quality gates, evidence requirements, 'no finding without proof'), but those are not a substitute for access control. Docker and bundled tooling increase supply-chain exposure; dependency hygiene/CVE status is not documented in the provided excerpt.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
70
AF Security Reliability

Best When

You need structured, evidence-based web app security testing with OWASP/PortSwigger coverage and can run it in an isolated environment with appropriate authorization.

Avoid When

You cannot control the tool’s runtime behavior (e.g., untrusted networks/targets), lack permission/scope, or need a purely passive scanner with no active probing/exploitation.

Use Cases

  • Automating web application security testing aligned with OWASP WSTG and PortSwigger technique references
  • Generating evidence-based pentest reports with reproducible CLI/curl-style commands
  • Assessing common vulnerability classes such as XSS, SQLi, SSRF, SSTI, IDOR, and related injection/auth/business-logic issues
  • Regression-style coverage verification of an app across repeated engagements
  • Agentic discovery and verification workflows with multi-stage proof requirements

Not For

  • Production incident response or on-the-fly triage without authorization/testing scope
  • Testing targets without explicit permission (it is designed for offensive/security testing)
  • Highly regulated environments where automated exploitation tooling is disallowed
  • Purposes other than web application security assessment (e.g., generic network scanning only)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: README implies it can be run offline (Ollama) or with Claude Code; no explicit auth method described for the MCP server API in provided README excerpt
OAuth: No Scopes: No

The provided README excerpt does not document authentication requirements for the MCP server (e.g., API keys, bearer tokens, or session auth). Therefore auth posture for programmatic access cannot be determined from available data.

Pricing

Free tier: No
Requires CC: No

No pricing/hosting model information was provided; repository appears to be open-source/self-hostable tooling.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Tooling is designed for active security testing; agents may generate high request volume (crawler/scanners). Ensure strict rate limiting/scope controls in your environment.
  • Because it orchestrates multiple phases and subagents, failures mid-phase may require resume/checkpointing; verify that checkpoints are correctly persisted in your runtime.
  • The README describes evidence/quality gates, but the excerpt does not show concrete MCP error schemas or retry/idempotency guarantees; agent implementations should treat operations as potentially non-idempotent.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for autopentest-ai.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered