walkaround
Launch check for AI-built apps: SAFE or DO NOT SHIP verdict, with evidence and paste-back fixes.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"walkaround": {
"url": "https://walkaround.dev/mcp"
}
}
}Remote endpoints
https://walkaround.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (2)
🟡scan_app(url)
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.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The app to check, e.g. https://example.com"
}
},
"required": [
"url"
]
}🟢get_receipt(receipt_id, token)
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.
Input Schema
{
"type": "object",
"properties": {
"receipt_id": {
"type": "string",
"description": "The receipt id, from scan_app."
},
"token": {
"type": "string",
"description": "Optional API credit token. Without it the receipt comes back folded."
}
},
"required": [
"receipt_id"
]
}Community
Evidence