Skip to content

ScanScam Integrity

by Gabothefounder · remote · no sign-in to list tools · v0.1.1 · published by GitHub user Gabothefounder

Independent agent preflight: verify change, mandates, evidence, and exact execution.

Changes · 2
CompareRegistry entry

2 tools: 2 change things.

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 scanscam-integrity https://www.scanscam.ca/api/integrity/v1/mcp --header 'Authorization: <your-authorization>'

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 2Claude Code: ask
  • integrity_discoverPublic, no-auth storefront for agents.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Public, no-auth storefront for agents. Returns what ScanScam Integrity can verify, the commercial model, and how to express demand. Do not send transaction data.

    Annotations the server declares

    • title: Discover ScanScam Integrity
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • integrity_request_serviceTell ScanScam what kind of independent service your agent needs, using categories only.No findings

    Why it is in this group

    • The name "integrity_request_service" says "request": a word for a change.
    Description, as the server wrote it
    Tell ScanScam what kind of independent service your agent needs, using categories only. This is a demand/fit signal, not a transaction submission.

    Annotations the server declares

    • title: Request an independent agent service
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false

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 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http scanscam-integrity https://www.scanscam.ca/api/integrity/v1/mcp --header 'Authorization: <your-authorization>'

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": [],
    "ask": [
      "mcp__scanscam-integrity__integrity_discover",
      "mcp__scanscam-integrity__integrity_request_service"
    ],
    "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 scanscam-integrity. Review it before you use it.