Web Pentest MCP Server

run_pentest_pipeline

Launches automated OWASP WSTG v4.2 web penetration tests for an authorized target, with selectable scope/profile, evidence capture (CLI stdout + SHA-256), and OWASP risk scoring.

Instructions

Master Penetration Testing Pipeline: Kích hoạt Pipeline Kiểm thử Tự động 1 Chạm theo chuẩn OWASP WSTG v4.2. Tự động thu thập bằng chứng pháp lý (Forensics CLI stdout + SHA-256 hash), tính điểm rủi ro theo ma trận 16 chỉ số OWASP Risk Rating.

📌 HƯỚNG DẪN THỰC HIỆN:

target_url: Nhập URL mục tiêu (ví dụ: 'http://127.0.0.1:8000' hoặc 'https://dichvucong.quangninh.gov.vn').
program_id: Chọn mã Program từ Dropdown (hoặc để trống để hệ thống tự động nhận diện từ URL).
test_scope: Chọn phạm vi kiểm thử qua Dropdown:
- 'full': Quét toàn diện tất cả các bài test WSTG khả dụng song song.
- 'section:WSTG-INFO': Quét nhóm Thu thập thông tin (Fingerprinting, OSINT, WAF).
- 'section:WSTG-CONF': Quét nhóm Cấu hình & Headers (HSTS, CSP, X-Frame-Options).
- 'objective:WSTG-INFO-02': Quét đúng 1 bài test cụ thể.
scan_profile: Chọn cấu hình quét ('recon_quick': quét nhanh ~10-15s; 'recon_deep': quét chuyên sâu kèm Nmap).
asset_tier: Cấp độ tài sản ('1'=Critical, '2'=Standard Production, '3'=Internal/Staging) để nhân hệ số rủi ro.
data_sensitivity: Phân loại dữ liệu ('L1', 'L2', 'L3', 'L4').

💡 VÍ DỤ MINH HỌA:

Ví dụ 1: Quét toàn diện nhanh trên hệ thống nội bộ: run_pentest_pipeline(target_url="http://127.0.0.1:8000", test_scope="full", scan_profile="recon_quick")
Ví dụ 2: Quét chuyên đề Cấu hình Web Server (CONF): run_pentest_pipeline(target_url="http://127.0.0.1:8000", test_scope="section:WSTG-CONF")

⚠️ CHÚ Ý BẢO MẬT: Mục tiêu BẮT BUỘC phải được cấp phép trước qua 'manage_scope_targets'. Hệ thống sẽ TỪ CHỐI THỰC THI (BLOCKED - TARGET_OUT_OF_SCOPE) nếu chưa được xác nhận ủy quyền.

Input Schema

Name	Required	Default
`asset_tier`	No	2
`program_id`	No
`target_url`	Yes
`test_scope`	No	full
`scan_profile`	No	recon_quick
`data_sensitivity`	No	L2

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Oct 30, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so: it discloses forensic evidence capture (CLI stdout + SHA-256 hash), 16-indicator OWASP risk rating, scan durations (~10-15s quick vs deep with Nmap), parallel execution, and the failure mode 'BLOCKED - TARGET_OUT_OF_SCOPE'. An agent knows the authorization gate, cost profile, and side effects before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then cleanly structured as numbered steps plus runnable examples. Some formatting noise (emoji headers, bilingual mix) and example redundancy add length, but nothing is truly wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. The definition covers prerequisites, scope granularity, profile tradeoffs, and the blocking condition — the only omission is what the L1-L4 sensitivity levels mean and how they interact with asset_tier scoring.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate: it explains target_url format with examples, program_id's blank-autodetect behavior, all test_scope variants, scan_profile speed tradeoff, and asset_tier's risk multiplier. It leaves data_sensitivity as a bare list of L1-L4 with no meaning attached, which is the one gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Master Penetration Testing Pipeline', launches a one-click automated OWASP WSTG v4.2 run) and contrasts with single-test invocation by noting it can run 'tất cả các bài test WSTG khả dụng song song'. It does not explicitly name run_wstg_test as the alternative, so sibling differentiation is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it (full/section/objective scope selection), gives two concrete invocation examples, and states the mandatory prerequisite: targets must be authorized via 'manage_scope_targets' beforehand. Alternatives and exclusions are effectively covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server