Skip to content

dev.walkaround/walkaround

by walkaround.dev · remote · no sign-in to list tools · v1.0.0 · published by dev.walkaround

Launch check for AI-built apps: SAFE or DO NOT SHIP verdict, with evidence and paste-back fixes.

Changes · 1
CompareRegistry entry

2 tools: 1 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http walkaround https://walkaround.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 1Claude Code: ask
  • scan_appRun twelve deterministic checks against the outside of a public web app and return a dated verdict: the stamp, the open/closed/not-checked counts, every line with its plain-English…No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run twelve deterministic checks against the outside of a public web app and return a dated verdict: the stamp, the open/closed/not-checked counts, every line with its plain-English consequence, what was skipped, and the receipt id and URL. Free, no token. It reads public pages only: it does not sign in, does not create an account and does not guess anything. A clean verdict is not a guarantee of safety.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: false
Only reads 1Claude Code: allow
  • get_receiptRead a receipt back as JSON by its id.No findings

    Why it is in this group

    • The name "get_receipt" says "get": a word for reading.
    Description, as the server wrote it
    Read a receipt back as JSON by its id. Folded, it returns the twelve lines and a pay object naming where a human pays. With a bearer token that has credit it unseals: the evidence and the fix paragraph for every open line, and the SOTA Security Model read of the app. One fixed price per unsealed report. 401 for a token we did not issue, 402 when the balance will not cover it.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http walkaround https://walkaround.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__walkaround__get_receipt"
    ],
    "ask": [
      "mcp__walkaround__scan_app"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as walkaround. Review it before you use it.