MandateShield AI Payment Evidence

by mandateshield.com · remote · no sign-in to list tools · v1.13.0 · published by com.mandateshield

Analyzes delegated AI payment authority and exposes supported Stripe/x402 evidence contracts.

Final · 3

Compare Registry entry

3 tools: 3 do something that can't be undone.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone3Claude Code: ask: see these tools
Changes things0Claude Code: ask
Only reads0Claude Code: allow

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

claude mcp add --transport http payment-authority https://mandateshield.com/api/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn2 info

Warnnormalize_agent_payment_protocol
The server marks "normalize_agent_payment_protocol" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "normalize_agent_payment_protocol" says "payment": a word that usually means money moves, which cannot be taken back.
What this check looks for
Infocheck_ai_payment_authority
The description mentions "credentials".
Matched text
description: "...r a production gate. Never send payment credentials or private keys."
What this check looks for
Infonormalize_agent_payment_protocol
The description mentions "credential".
Matched text
description: "...rifies delegated authority or a payment credential and always returns enforcement_authoriz..."
What this check looks for

Tools

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

3 tools

Can't be undone 3Sends, pays, publishes or merges: once done, it cannot be taken back.Claude Code: ask

check_ai_payment_authorityUse before an AI agent buys, subscribes, transfers value, calls a metered API, or accesses a paid resource when the user wants a payment-authority check.Can send data out1 finding
Why it is in this group
- The name "check_ai_payment_authority" says "payment": a word that usually means money moves, which cannot be taken back.
What it can reach
- outboundThe input takes a URL (input.http_request.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
  The description mentions "credentials".
  Matched text
  description: "...r a production gate. Never send payment credentials or private keys."
  What this check looks for
Description, as the server wrote it
Use before an AI agent buys, subscribes, transfers value, calls a metered API, or accesses a paid resource when the user wants a payment-authority check. Analyze whether the proposed purchase fits supplied policy facts. This v1 entry check is non-executable and always returns enforcement_authorized=false; use the strict cryptographic tool for a production gate. Never send payment credentials or private keys.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
normalize_agent_payment_protocolUse when an agent encounters an AP2 terminal closed-payment projection, x402 v2 PAYMENT-REQUIRED offer, or explicitly profiled MPP Payment challenge and needs the supported fields …2 findings
Why it is in this group
- The name "normalize_agent_payment_protocol" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
  The description mentions "credential".
  Matched text
  description: "...rifies delegated authority or a payment credential and always returns enforcement_authoriz..."
  What this check looks for
- Warn
  The server marks "normalize_agent_payment_protocol" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "normalize_agent_payment_protocol" says "payment": a word that usually means money moves, which cannot be taken back.
  What this check looks for
Description, as the server wrote it
Use when an agent encounters an AP2 terminal closed-payment projection, x402 v2 PAYMENT-REQUIRED offer, or explicitly profiled MPP Payment challenge and needs the supported fields projected before an authority check. Map those documented fields into a deterministic MandateShield purchase envelope. X402 requires source-matched network+payTo identity and MPP requires source-matched HTTPS service-origin+method identity; merchant_id alone is insufficient. Evidence references are not independently verified. projection_fields_valid is not full protocol conformance: this tool never verifies delegated authority or a payment credential and always returns enforcement_authorized=false under assurance.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
verify_cryptographic_payment_authorityUse only for a production pre-payment authority gate after the caller has a registered mandate, pinned issuer key, fresh challenge, VERIFY-scoped key, exact final purchase and supp…No findings
Why it is in this group
- The name "verify_cryptographic_payment_authority" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it
Use only for a production pre-payment authority gate after the caller has a registered mandate, pinned issuer key, fresh challenge, VERIFY-scoped key, exact final purchase and supported signed evidence. Fail closed for JWS, an AP2-shaped closed-payment SD-JWT projection with RFC 9901 KB-JWT, or normalized TAP-shaped RFC 9421-style evidence. Full AP2 checkout/delegate-chain and Visa TAP structured-field/trust-store processing remain external. A qualifying live ALLOW creates only a short RESERVED authorization and cumulative-budget allocation. This MCP tool never executes payment and exposes no processor transition: a separate trusted gateway with an audience-bound PROCESSOR key must CONSUME and freshly redeem the provider-bound permit before attempting an idempotent provider operation, then reconcile the outcome.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- 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.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; check_ai_payment_authority

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 14:35 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 3
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 irreversible). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://mandateshield.com/api/mcp: tools/list returned 3 tools to an anonymous client, including check_ai_payment_authority (irreversible), normalize_agent_payment_protocol (irreversible), verify_cryptographic_payment_authority (irreversible)
What this check looks for

Install

Pinned to version 1.13.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http payment-authority https://mandateshield.com/api/mcp

Run in a terminal.

Claude Code permissions

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

.claude/settings.json

{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__payment-authority__check_ai_payment_authority",
      "mcp__payment-authority__normalize_agent_payment_protocol",
      "mcp__payment-authority__verify_cryptographic_payment_authority"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as payment-authority. Review it before you use it.

Capability tags behind 1 rule

mcp__payment-authority__check_ai_payment_authority outbound

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.mandateshield/payment-authority/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 17:58 UTC.

For agents: Markdown · JSON · report this listing