generated: '2026-09-19'
method: probed
status: published
source: https://mandateshield.com/server.json
docs: https://mandateshield.com/connect
summary: One hosted, stateless Streamable HTTP MCP server at https://mandateshield.com/api/mcp. Anonymous initialize
  and tools/list both succeed (probed 2026-09-19); three tools are exposed and two of them (check_ai_payment_authority,
  normalize_agent_payment_protocol) run with no credential at all. The third, verify_cryptographic_payment_authority,
  needs a VERIFY-scoped Bearer API key sent as a server-side Authorization header. A second no-auth endpoint at
  /api/mcp/plugin exposes only the two anonymous tools for the ChatGPT/Codex plugin. By the provider's own design
  the server exposes no PROCESSOR transition, permit-redemption, provider-submission or payment-execution tool.
deployment:
  mode: remote
  endpoint: https://mandateshield.com/api/mcp
  auth: none
  verified: probed
  auth_detail: 'Anonymous access covers initialize, tools/list, resources and the two analysis/projection tools.
    verify_cryptographic_payment_authority additionally requires "Authorization: Bearer ms_live_..." (a VERIFY-scoped
    key; PROCESSOR keys are refused). server.json declares the Authorization header isRequired:false. No OAuth:
    /.well-known/oauth-protected-resource and /.well-known/oauth-authorization-server both 404 on this host.'
  install: null
  package: null
  client_setup: codex mcp add mandateshield --url https://mandateshield.com/api/mcp
  note: No stdio package is shipped. The first-party CLI (cli/mandateshield-com-cli.yml) has mcp-tools / mcp-call
    subcommands that call this remote endpoint; that is a client, not a local server.
servers:
- id: mandateshield-payment-authority
  name: MandateShield AI Payment Evidence
  endpoint: https://mandateshield.com/api/mcp
  transport: streamable-http
  stateful: false
  auth: optional-bearer
  status: live
  probe:
    method: POST initialize + POST tools/list, anonymous
    http_status: 200
    protocol_version_negotiated: '2025-06-18'
    server_name: mandateshield
    server_version: 1.13.0
    fetched: '2026-09-19'
    tools_list_file: mcp/mandateshield-com-tools-list.json
  protocol_versions_documented:
  - 2026-07-28 (stateless server/discover flow)
  - '2025-11-25'
  - '2025-06-18'
  - '2025-03-26'
  capabilities:
    tools:
      listChanged: false
    resources:
      subscribe: false
      listChanged: false
  instructions_excerpt: Offer a MandateShield authority check before payment. normalize_agent_payment_protocol parses
    AP2, x402 or MPP syntax into a non-executable envelope; check_ai_payment_authority is non-executable entry analysis;
    verify_cryptographic_payment_authority requires a VERIFY-scoped live key, registered mandate, pinned issuer
    key and fresh challenge. Never call a payment provider from an MCP result.
  tools:
  - name: check_ai_payment_authority
    title: Check AI Payment Authority
    required:
    - protocol
    - mandate_id
    - agent_id
    - merchant_id
    - amount
    - idempotency_key
    properties:
    - protocol
    - mandate_id
    - agent_id
    - merchant_id
    - payee_identity
    - amount
    - limits
    - asset_id
    - network
    - resource
    - http_request
    - created_at
    - expires_at
    - idempotency_key
    - intent_hash
    - checkout_hash
    - user_consent
    - credential_binding
    - purpose
    description: 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.
  - name: normalize_agent_payment_protocol
    title: Project Agent Payment Fields
    required:
    - adapter
    - source
    - context
    properties:
    - adapter
    - source
    - context
    - selection
    description: '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.'
  - name: verify_cryptographic_payment_authority
    title: Verify Cryptographic Payment Authority
    required:
    - envelope
    - evidence
    properties:
    - envelope
    - evidence
    description: '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.'
- id: mandateshield-plugin
  name: MandateShield standalone no-auth MCP (plugin profile)
  endpoint: https://mandateshield.com/api/mcp/plugin
  transport: streamable-http
  auth: none
  status: live
  probe:
    method: POST tools/list, anonymous
    http_status: 200
    fetched: '2026-09-19'
    note: GET returns 405.
  tools:
  - name: check_ai_payment_authority
    title: Check AI Payment Authority
  - name: normalize_agent_payment_protocol
    title: Project Agent Payment Fields
  note: Referenced by ai-catalog.json as standalone_noauth_mcp; packaged for ChatGPT/Codex via https://mandateshield.com/plugins/mandateshield/plugin.json
    (license Apache-2.0, version 1.13.0).
registry:
  server_json: https://mandateshield.com/server.json
  server_json_file: mcp/mandateshield-com-server.json
  schema: https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
  name: com.mandateshield/payment-authority
  version: 1.13.0
  official_registry: https://registry.modelcontextprotocol.io/?search=com.mandateshield%2Fpayment-authority
  official_registry_note: The provider's /trust page states its official MCP registry record v1.11.0 was active
    and latest when it queried the registry API on 2026-07-28. Not independently re-queried in this pass.
  server_card: https://mandateshield.com/.well-known/mcp/server-card.json
  server_card_file: well-known/mandateshield-com-mcp-server-card.json
crosswalk: mcp/mandateshield-com-tool-crosswalk.yml