Skip to content

ScopeProof

by davisvillelabs · remote · no sign-in to list tools · v0.1.0 · published by GitHub user davisvillelabs

Machine-verifiable authorization checks for autonomous AI agents.

Changes · 3
CompareRegistry entry

3 tools: 3 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 scopeproof https://scopeproof.davisvillelabs.com/mcp

Tools

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

3 tools

Changes things 3Claude Code: ask
  • scopeproof.check_actionPaid $0.01 deterministic comparison of one proposed action against one supplied authority envelope.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.
    Description, as the server wrote it
    Paid $0.01 deterministic comparison of one proposed action against one supplied authority envelope. Returns within_scope, outside_scope, or review_required plus an Ed25519-signed receipt. ScopeProof does not authenticate the authority issuer, grant platform permission, replace Muse or another host approval check, or execute or fetch the target.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • scopeproof.preflightFree structural and secret-safety validation.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
    Free structural and secret-safety validation. Does not return an authorization verdict.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • scopeproof.verify_receiptFree cryptographic verification of a ScopeProof authorization receipt.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
    Free cryptographic verification of a ScopeProof authorization receipt.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http scopeproof https://scopeproof.davisvillelabs.com/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": [],
    "ask": [
      "mcp__scopeproof__scopeproof_preflight",
      "mcp__scopeproof__scopeproof_check_action",
      "mcp__scopeproof__scopeproof_verify_receipt"
    ],
    "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 scopeproof. Review it before you use it.