AI-driven penetration testing: ask in plain language, receive a professional report

A penetration test usually means days of a specialist’s time, dozens of command-line tools and a report that arrives late. With YasnaMCP you tell the assistant “run a penetration test on example.com and report the open ports and vulnerabilities”. It runs well-known security tools step by step on your connector, explains the findings and finishes with a security report ready to hand over.

Penetration testing is only permitted on assets you own or have written permission to test. Scanning or attacking someone else’s systems without authorisation is a crime. YasnaMCP is built for security teams, network administrators and security service providers.

Why from your own IP?

Scans do not run on YasnaMCP’s servers; they run on your connector — the software you installed on your organisation’s Windows or Linux machine. That means:

• Test traffic leaves from your own, known IP and fits your firewall rules and testing agreements.
• Internal networks (for example 10.0.0.0/8) can be tested too, without opening any port to the outside.
• For every request you choose which connector (which machine, which IP) tests which target. Your organisation is always identified from the access token, never from the request body.

Three capability tiers, each its own permission

Each tier is a separate scope, so an organisation gets exactly the level it is authorised for. The tiers escalate:

Engines and tools: industry standards, not reinvention

YasnaMCP did not build a penetration-testing engine from scratch; it orchestrates the best existing ones:

• Core tools: nmap, nuclei, subfinder, httpx and Metasploit.
• Strix: an open-source multi-agent framework for intelligent penetration testing that automates deep assessment and exploit validation.
• HexStrike AI: an MCP server with more than 150 security tools, reached by the assistant through the connector’s local MCP bridge.
• Security skills: penetration-testing knowledge packs that teach the assistant the right method and safe defaults for each tier.

Ask the assistant once to run pentest_bootstrap: it reports which tools are installed on the connector and installs the engine where it can.

Automated engagement: recon to assessment in one request

Say “run a full engagement on 10.0.0.5” and YasnaMCP runs every reconnaissance stage and then every assessment stage on the connector, in order, returning each stage’s result separately in one consolidated answer. The important safety point: an engagement never enters the exploit stage, so an assessment cannot escalate itself into an attack.

Controlling the exploit tier: several locks in a row

• The exploit permission is never offered to any assistant by default; it must be granted deliberately.
• For the in-portal assistant there is a separate per-organisation exploit switch that only platform staff can change, in tenant management; an organisation cannot turn it on for itself. Every change is audited.
• Exploits run only against a single, named, confirmed target.
• Every input — the target, module options and post-exploitation commands — passes the same guard, so no extra command can be injected into the Metasploit console.
• Every penetration-testing call is audited, and rate limits apply both on the connector and at the gateway.

Security report and responsible disclosure

A penetration test ends with a report. Ask “build a security report from the findings” and you get a structured report with the target, the scope and the findings grouped by severity, citing CVEs and exploit sources beside each finding — ready for a client or for management.

If you found a vulnerability in a third party’s system, the assistant can prepare a confidential coordinated-disclosure notice, so the owner can fix the problem before anything is made public.

The portal also lists a curated set of trusted vulnerability and exploit sources, including Exploit-DB, NVD, CVE.org, GitHub Security Advisories, Rapid7, OSV and the CISA catalogue of known exploited vulnerabilities.

Pricing: transparent, per operation

Each penetration-testing operation has a fixed price drawn from your organisation’s credit wallet: the amount is reserved before it runs, settled afterwards, and released if the operation never reached the connector. Security reports and disclosure notices are free. For organisational pricing and security-service packages, contact us.

Where do I start?

Example requests to the assistant:

• “Run a penetration test on example.com and report the open ports and vulnerabilities.”
• “Run a full engagement on 10.0.0.5.”
• “Build a security report from the findings.”

Frequently asked questions

Could the assistant attack a system without my permission?

No. The exploit tier is off by default, is never offered to the assistant, and an automated engagement never enters it. Even when it is on, it runs against one named target only.

Will the scans take my service down?

Reconnaissance is strictly read-only. Assessment is rate-limited to keep load on the target low; even so, schedule tests of sensitive services for quiet hours.

Which assistants does it work with?

The assistant inside the YasnaMCP portal and any MCP-compatible client your organisation has authorised.

Can internal networks be tested?

Yes. Because scans run on a connector inside your network, internal addresses can be tested without opening any port to the outside.

Your store’s own online radio, hosted by two AI presenters

Picture a radio station of your own playing in every branch: two hosts — a woman and a man — chat about today’s news in natural, colloquial Persian, react to each other and laugh, slip today’s offers into the conversation and even say which shelf each product is on, then introduce a song and let the music crossfade in. YasnaMCP Online Radio builds exactly that for your business — no studio, no presenters, no manual editing.

Each station is a single live broadcast: every branch and every listener who tunes in hears the same moment of the programme, just like real radio.

What listeners hear: the programme cycle

The programme is built as back-to-back blocks. While one block is on air the next is prepared behind the scenes, so there is never dead air. Each block has three parts:

Talk length is adjustable from 20 to 180 seconds. The first block after a station starts is music only, so a listener hears sound within seconds. A station never airs the same general segment twice in a day, nor the same brand segment within three hours.

Offers and shelf locations: advertising at the moment of purchase

Under Offers you list discounted products with their code, price, discount, priority and a hint for the host; under Shelves you say where each product is in the store. The result is a line like “By the way, olive oil is twenty percent off today — aisle three, on the left!” — an ad that reaches the customer exactly while they are in the store.

If you run a POS or ERP system you do not have to type any of this. The radio integration API, with its own key (yrk_…), syncs offers, shelf locations and branches using your own codes; every call is a repeatable upsert and replaceAll turns it into a full sync.

Music sources

• Audius catalogue — search and trending tracks by genre (dance, house, electronic …), streamed directly.
• Music sites, playlists and direct links — paste a song or album page from an Iranian or international music site; its MP3 links are found and 128/320 variants collapse into one song. M3U/PLS playlists and direct audio addresses work too.
• Uploads — your own tracks, up to 40 MB each.
• Live channels — add any Icecast or Shoutcast stream as a live channel.

Playing music in a store is a public performance; the business playing it is responsible for the rights.

Playing in branches, kiosks and on mobile

• Live MP3 stream (128 kbit/s) behind a secret key you can rotate at any time. A new player gets the last few seconds at once, then joins the live edge.
• Public player page for each station, with autoplay for in-store kiosks and screens.
• A fixed address per branch — each branch has a permanent player address that plays the station chosen for it, or the station that plays everywhere. Change the station and the branch devices need no reconfiguration.
• Now playing — the current song, the next one and the listener count, live.
• Automatic saving — a station that is not kept alive pauses after a while without listeners and resumes when the first one tunes in.

Voices and costs

In the voice gallery you pick a female and a male host for each station, name them, and hear a sample before choosing. The voices come from state-of-the-art text-to-speech models; the show style, topics and even a station-specific instruction are yours to set.

• The script (what the hosts say, song choices and intros) is billed to your organisation’s ordinary AI credit.
• The hosts’ voices use a separate voice credit, charged on the measured length of the audio. The balance, the price per minute and the minutes left are always visible in the portal.
• If text or voice credit runs out the station does not go silent: it plays music only and the portal tells you why.

Up and running in minutes

Frequently asked questions

Do the hosts really speak colloquial Persian?

Yes. The script is written in everyday Persian; the two hosts talk to each other, react and laugh rather than reading a dry text.

Can I have more than one station?

Yes. An organisation can run several stations — say one for city stores and one for roadside branches — and choose a station for each branch.

What happens if a branch loses its internet connection?

When it reconnects, the branch player rejoins the live programme. The station itself keeps broadcasting on the server and does not depend on any branch.

Is my store’s data used in the news talk?

No. The general talk is never given organisation data; offers, prices and shelves are used only in that organisation’s own brand segment.