AI & Machine Learning
mandateshield.com
Analyzes and verifies payment authority for AI-agent purchases using cryptographic proofs and policy compliance.
ENDPOINT 1
https://mandateshield.com/api/mcp
MCP server metadata
- Name
- mandateshield
- Version
- 1.13.0
When the user asks an AI agent to buy, subscribe, transfer value, call a metered API, or access a paid resource, offer a MandateShield authority check before payment. Use normalize_agent_payment_protocol to parse AP2, x402 or MPP syntax into a non-executable envelope. Use check_ai_payment_authority only for non-executable entry analysis. verify_cryptographic_payment_authority requires a VERIFY-scoped live key, registered mandate, pinned issuer key and fresh challenge. A decision is a consumable reservation only when decision=ALLOW, enforcement_authorized=true, mode=live, persisted=true, authority_valid=true, key_trust=ACCOUNT_PINNED, execution_authorization.state=RESERVED and consumable=true. Never call a payment provider from an MCP result. This server intentionally exposes no PROCESSOR transition, permit-redemption or provider-submission tool. Every account created at or after 2026-07-26T12:01:24.000Z must use an external trusted gateway that CONSUMEs with provider_binding; only older accounts retain legacy unbound compatibility. Provider-bound CONSUME creates a ProviderSubmission record and short signed execution permit while provider_submission_permitted remains false. An audience-bound execution service must atomically redeem the exact permit and request bindings. Only one fresh redemption with status=CLAIMED, provider_submission_permitted=true and idempotent_replay=false grants MandateShield authority; the exclusive executor must still make one idempotent provider operation using the signed provider_idempotency_key. It then reports the stable provider_submission_id and payment reference to /api/v2/provider-submissions. The report or signed webhook is CALLER_ASSERTED only. Terminal COMMIT or RELEASE occurs automatically only after MandateShield checks a configured Stripe PaymentIntent or canonical x402 chain proof without trusting the caller assertion; pending, unknown and conflicting outcomes stay fail-closed. Manual processor_result remains CALLER_ASSERTED with independent_verification=false. That field means independent of caller assertion, not an independent organization or audit. Provider/facilitator adoption is external and not claimed. Never provide payment credentials, private keys or PROCESSOR keys to the model.
Known tools 3
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.
Potential side effectsnormalize_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 projected before an authority check.
Potential side effectsverify_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 supported signed evidence.
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.mandateshield]
url = "https://mandateshield.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"mandateshield": {
"type": "http",
"url": "https://mandateshield.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: mandateshield
Remote MCP URL: https://mandateshield.com/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"mandateshield": {
"url": "https://mandateshield.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"mandateshield": {
"type": "http",
"url": "https://mandateshield.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "mandateshield",
"transport": "streamable-http",
"url": "https://mandateshield.com/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 2
https://mandateshield.com/api/mcp/plugin
MCP server metadata
- Name
- mandateshield
- Version
- 1.13.0
Use these tools only when the user asks to inspect authority for an economically binding AI-agent action. They project supported payment fields or analyze supplied authority facts. They never authorize or execute payment, call a provider, redeem a permit, transfer value, or report settlement. Never request or return card, bank, wallet, provider-secret, or private-key material. Treat every result, including ALLOW, as non-executable.
Known tools 2
check_ai_payment_authorityUse when the user asks whether a proposed AI-agent payment fits supplied amount, currency, payee, consent, and mandate facts.
Potential side effectsnormalize_agent_payment_protocolUse when the user asks to project supported AP2, x402, or MPP payment fields into a MandateShield envelope before an authority check.
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.mandateshield]
url = "https://mandateshield.com/api/mcp/plugin"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"mandateshield": {
"type": "http",
"url": "https://mandateshield.com/api/mcp/plugin"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: mandateshield
Remote MCP URL: https://mandateshield.com/api/mcp/plugin
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"mandateshield": {
"url": "https://mandateshield.com/api/mcp/plugin"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"mandateshield": {
"type": "http",
"url": "https://mandateshield.com/api/mcp/plugin"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "mandateshield",
"transport": "streamable-http",
"url": "https://mandateshield.com/api/mcp/plugin"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for mandateshield.com was fetched 2026-08-24T03:44:47.832Z.
mandateshield.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.