---
title: "Protect MCP receipt verifier: review, role & definition · Undominated.ai"
canonical: https://undominated.ai/agents/wshobson-receipt-verifier/
description: "A receipt-review component that separates valid signatures, invalid signatures and undecidable verification."
---

# Protect MCP receipt verifier: review, role & definition · Undominated.ai

> A receipt-review component that separates valid signatures, invalid signatures and undecidable verification.

[← Explore all agents](/agents/)

SECURITY WORKFLOW COMPONENTS / Seth Hobson

# Protect MCP receipt verifier

A receipt-review component that separates valid signatures, invalid signatures and undecidable verification.

 [Use this definition ↓](#setup)[Original source ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/agents/receipt-verifier.md)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 4 linked sources
 Publisher Seth Hobson
 Licence [MIT ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE)
 Revision 46891e7e60da
 [Read what was—and wasn’t—checked ↓](#review)

“Expert in Ed25519 signed receipts, JCS canonicalization, and offline verification. Use when you need to verify receipt authenticity, audit a receipts file, detect tampering, or explain why verification failed.”

 [Seth Hobson · upstream description ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/agents/receipt-verifier.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The profile uses the external public key rather than trusting a key embedded in an untrusted receipt.
- For the documented protect-mcp 0.7.4 format, it explicitly says receipts lack a previous-record hash and cannot reveal deleted or reordered lines.

### A good fit for

 - Supply receipt JSONL and a public key obtained independently from the signed records.
- Return per-file verification outcomes and an explanation of what the signature does and does not establish.

### Weigh up before choosing

 - A signature failure can mean a wrong key or malformed record, so the source’s tampering attribution must be softened. Signed tool names do not prove policy enforcement or actual tool effects.
- Source-only component: inspect its upstream context and dependencies before adapting it; no standalone runnable bundle is offered.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/protect-mcp/agents/receipt-verifier.md (pinned complete source retained)
- LICENSE
- Repository README and current official host configuration documentation
- plugins/protect-mcp/README.md

### Our findings

 - The profile uses the external public key rather than trusting a key embedded in an untrusted receipt.
- For the documented protect-mcp 0.7.4 format, it explicitly says receipts lack a previous-record hash and cannot reveal deleted or reordered lines.

### Not established by this review

 - Source review only: no agent was installed or invoked. Task correctness, effective host restrictions and integration behaviour were not tested.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Use the role in your project.

[Upstream setup instructions ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/agents/receipt-verifier.md)
 - Read the pinned source and its licence, then configure an explicitly bounded host context.
- Preinstall and inspect the pinned verifier before offline use; an npx invocation can fetch packages. Preserve originals and verify the key through a separate trusted channel.
- Supply receipt JSONL and a public key obtained independently from the signed records.

### Before you start

 - Receipt JSONL and independently trusted public key
- Matching protect-mcp format and @veritasacta/verify runtime

### Compatibility

Claude Code

### Implementation

Markdown

### Host-mediated agent profile

 - No tools allowlist is declared. Claude Code can inherit or expose the host’s available tools by default; restrict file, shell and network access in the host.

### Cost model

The definition has the stated open-source licence. Model/host usage and any connected service or execution environment can incur separate costs.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned upstream agent definition ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/agents/receipt-verifier.md) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/agents/receipt-verifier.md Supports: Workflow, inputs, outputs and stated boundaries
- [Applicable licence ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE Supports: Redistribution and attribution
- [Host configuration and tool inheritance ↗](https://code.claude.com/docs/en/sub-agents.md) Checked 2026-10-14 https://code.claude.com/docs/en/sub-agents.md Supports: Host loading and effective permission boundaries
- [Pinned inspected source: plugins/protect-mcp/README.md ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/README.md) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/protect-mcp/README.md Supports: Dependency setup and source-review boundary

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Claude Security code explorer ↗ A Claude Security search component that maps one code path for a caller and returns file/line evidence.](/agents/anthropic-explore/)[### Claude Security patch generator ↗ A security-fix component that stages one narrow change in an orchestrator-created scratch checkout.](/agents/anthropic-patch-generator/)[### Claude Security patch verifier ↗ A security-patch verifier that derives the staged diff and separates tested behavior from source-only confidence.](/agents/anthropic-patch-verifier/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
