Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

sh.agentcard/agentcard

REMOTE · MCP.AGENTCARD.SH · SCANNED SEP 20

Prepaid virtual cards for AI agents: one-time cards, spend caps, human approvals.

Available components

+1 this week 90 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 10304 tokens (~177/item across 58 items; 58 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management98
  • Stability check failed: schema churn in the 30 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 8 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety96
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 6 of 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_preset" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
  • An AI judge read all 59 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the sh.agentcard/agentcard MCP server?

sh.agentcard/agentcard is a hosted endpoint at https://mcp.agentcard.sh/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.agentcard.sh

# add to Claude Code
claude mcp add --transport http sh-agentcard-agentcard 'https://mcp.agentcard.sh/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "sh-agentcard-agentcard": {
      "url": "https://mcp.agentcard.sh/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "sh-agentcard-agentcard": {
      "type": "http",
      "url": "https://mcp.agentcard.sh/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.sh-agentcard-agentcard]
url = "https://mcp.agentcard.sh/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sh-agentcard-agentcard": {
      "type": "remote",
      "url": "https://mcp.agentcard.sh/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add sh-agentcard-agentcard --url 'https://mcp.agentcard.sh/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  sh-agentcard-agentcard:
    url: "https://mcp.agentcard.sh/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "sh-agentcard-agentcard": {
      "Transport": "http",
      "Url": "https://mcp.agentcard.sh/mcp"
    }
  }
}
# add to Vellum
assistant mcp add sh-agentcard-agentcard -t streamable-http -u 'https://mcp.agentcard.sh/mcp'
// mcp.json
{
  "mcpServers": {
    "sh-agentcard-agentcard": {
      "type": "http",
      "url": "https://mcp.agentcard.sh/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 17 Sept 26 +1
    • A breaking change shipped without a version bump: still 1.0.0 security
    • Tool “allow_card_merchant” rewrote its description, which is the text the model reads security
    • Tool “create_card” rewrote its description, which is the text the model reads security
    • Tool “delete_preset” rewrote its description, which is the text the model reads security
    • Tool “get_card_preset” rewrote its description, which is the text the model reads security
    • Tool “get_wallet_link” rewrote its description, which is the text the model reads security
    • Tool “list_cards” rewrote its description, which is the text the model reads security
    • Tool “set_card_preset” rewrote its description, which is the text the model reads security
    • Tool “submit_kyc_document” rewrote its description, which is the text the model reads security
    • “get_card_preset” made “card_id” required, so existing callers break functional
    • “set_card_preset” made “card_id” required, so existing callers break functional
    • “save_preset” added an optional parameter “categories” cosmetic
    • “save_preset” added an optional parameter “currencies” cosmetic
    • “save_preset” added an optional parameter “mode” cosmetic
    • “add_funds” reworded the description of “payment_method” cosmetic
    • “allow_card_merchant” reworded the description of “card_id” cosmetic
    • “create_card” reworded the description of “preset” cosmetic
    • “get_card_preset” reworded the description of “card_id” cosmetic
    • “set_card_preset” reworded the description of “card_id” cosmetic
    • “allow_card_merchant” dropped the optional parameter “scope” cosmetic
    • “get_card_preset” dropped the optional parameter “for_app” cosmetic
    • “save_preset” dropped the optional parameter “only_categories” cosmetic
    • “save_preset” dropped the optional parameter “only_currencies” cosmetic
    • “save_preset” dropped the optional parameter “watch_categories” cosmetic
    • “save_preset” dropped the optional parameter “watch_currencies” cosmetic
    • “set_card_preset” dropped the optional parameter “for_app” cosmetic
  • 11 Sept 26 0
    • New tool “name_card” functional
    • New tool “recommend_card” functional
  • 10 Sept 26 0
    • Schema quality: 8585 → 10204 functional
    • Destructive annotations: 6 of 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_preset" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. functional
    • New tool “allow_card_merchant” functional
    • New tool “delete_preset” functional
    • New tool “get_card_preset” functional
    • New tool “list_presets” functional
    • New tool “save_preset” functional
    • New tool “set_card_preset” functional
    • “create_card” added an optional parameter “pending_card_id” cosmetic
    • “create_card” added an optional parameter “preset” cosmetic
    • “create_card” added an optional parameter “purchase_key” cosmetic
    • “create_card” reworded the description of “scope_preset” cosmetic
  • 8 Sept 26 0
    • Tool “create_card” rewrote its description, which is the text the model reads security
    • Tool “get_wallet_link” rewrote its description, which is the text the model reads security
    • Tool “list_cards” rewrote its description, which is the text the model reads security
    • “get_wallet_link” added an optional parameter “purpose” cosmetic
    • “create_card” reworded the description of “restart_setup” cosmetic
    • “create_card” reworded the description of “source” cosmetic
  • 27 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90.

  • 26 Aug 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Aug 26 +1
    • A breaking change shipped without a version bump: still 1.0.0 security
    • Tool “add_card” was removed security
    • Tool “create_card” rewrote its description, which is the text the model reads security
    • Tool “get_instructions” rewrote its description, which is the text the model reads security
    • Tool “get_wallet_link” rewrote its description, which is the text the model reads security
    • Tool “list_added_cards” rewrote its description, which is the text the model reads security
    • Tool “remove_added_card” rewrote its description, which is the text the model reads security
    • “close_card” added an optional parameter “approval_id” cosmetic
    • “create_card” added an optional parameter “restart_setup” cosmetic
    • “create_card” reworded the description of “connected_card_id” cosmetic
    • “create_card” reworded the description of “source” cosmetic
  • 15 Aug 26 0
    • Tool “get_wallet_link” rewrote its description, which is the text the model reads security
    • “get_wallet_link” added an optional parameter “amount_cents” cosmetic
    • “get_wallet_link” added an optional parameter “merchant” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://mcp.agentcard.sh/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.agentcard.sh CN=WE1,O=Google Trust Services,C=US 26 Jul 2026 24 Oct 2026 ECDSA 256 ECDSA-SHA256 c7c62f1e2c602fc60e2e1649875e2365
SANs: mcp.agentcard.sh
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.agentcard.sh. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
sh. present 55297 8 Verified
agentcard.sh. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://mcp.agentcard.sh/.well-known/oauth-protected-resource/mcp"

Bearer resource_metadata="https://mcp.agentcard.sh/.well-known/oauth-protected-resource/mcp"

Protected resource metadata

Document https://mcp.agentcard.sh/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://mcp.agentcard.sh/mcp
Authorisation server https://mcp.agentcard.sh/

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.agentcard.sh/mcp Verified 200
http (plaintext) http://mcp.agentcard.sh/mcp HTTPS enforced 301 https://mcp.agentcard.sh/mcp
MCP tools · 58 exposed · ~10,270 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
add_funds ~264

Generate a secure checkout link the user opens to add cash to their own balance (the money that funds new cards) via Apple Pay or Google Pay, in USD. Calling this tool moves NO money and initiates NO transfer: it only prepares a single-use hosted payment page — the exact equivalent of the user clicking 'Add funds' in the dashboard. The user personally reviews, authorizes, and completes (or abandons) the payment in their own browser with their own payment method; you never see or handle payment credentials. If a one-time phone verification is needed first, this tool automatically sends the user a code and tells you where it went: ask the user for the code, call verify_phone with it, then call add_funds again.

NameTypeReqDescription
amount_centsnumberyesAmount to add in cents (e.g. 5000 = $50.00). Typical range: $20.00 to $10,000.00 (2000 to 1000000 cents); the exact range depends on the active funding provider and is returned by the API when the am…
payment_methodstringPayment method for the checkout: apple_pay or google_pay. Ask the user which one their device has; apple_pay only when unknown.
NameTypeReqDescription
amountUsdstringAmount of the created checkout in USD.
checkoutUrlstringSingle-use payment link to hand the user verbatim (present when a checkout was created).
messagestringyesHuman-readable result or next step.

No examples provided.

allow_card_merchant ~92

Remember a merchant on a card so the next matching charge is allowed even when the card's category or merchant rules would otherwise deny it. One tool call — does not replace the rest of the preset.

NameTypeReqDescription
card_idstringCard id (from list_cards).
patternstringyesMerchant name pattern to remember, e.g. "STARBUCKS" or "ODD CAFE".
NameTypeReqDescription
messagestringyes
messagesarrayCard scope: where the remember is enforced.
needsNewCardbooleanCard scope: true when the card keeps a network category allowlist the remember cannot widen.
patternstring
policyVersionnumber
presetobject|null
scopestring
summarystring

No examples provided.

approve_request ~195

Resolve a pending approval request (approve or deny) once the USER has decided. Use this after get_card_details or create_card returns a 202 requiring approval, or for a row from list_pending_approvals. For card_details and transaction, approval automatically completes the follow-up action and returns the result. For cross_app actions (asks from another app: close/pause/resume a card, change a limit, view details), approval records the user's consent and the REQUESTING app completes the action from its side when it retries with the approval id.

NameTypeReqDescription
actionstringyesThe original action type from the approval prompt (list_pending_approvals rows carry it as action).
approval_idstringyesThe approval request ID
decisionstringyesWhether to approve or deny the request
resource_idstringyesCard ID (for card_details and cross_app actions) or approval ID (for transaction)
NameTypeReqDescription
actionstringThe original action type from the approval prompt: 'card_details' or 'transaction'.
cardobjectThe card resource returned by the approved follow-up action, when applicable.
decisionstringThe decision that was applied: 'approved' or 'denied'.
messagestringyesHuman-readable summary of the approval outcome and any follow-up action.
statusstringOutcome of the request: 'denied', 'card_details', 'card_created', 'resolved' (cross_app approvals: consent recorded, the requesting app completes the action), 'personal_surface_only' (company-connect…

No examples provided.

buy ~521

Shop and check out, in natural language, across the merchants the user has linked (DoorDash, etc.). Pass the whole ask as `request` — e.g. "order a caesar salad from Zuni on DoorDash" — and this tool runs the shopping flow for you. It is CONVERSATIONAL: this tool RETURNS a `conversation_id`; pass that SAME `conversation_id` back on every follow-up (your reply to a question, "add a coke", "yes, check out") so it continues the SAME order. Omit it (or set new_order=true) only to start a fresh order. It will ask for the delivery address and have you confirm the cart and total. CHECKOUT (which charges a one-time card) happens ONLY after the user explicitly confirms in a later message — relay the confirmation through `request` ("yes, place the order") on the SAME conversation_id. RELAY REPLIES VERBATIM: when the user answers a question from this tool ("yes", "the 16 oz one", "use my other card"), pass their reply through `request` as-is on the same conversation_id — do NOT rewrite it into a fresh full order command; a rewritten command reads as a NEW ask and the confirmation never lands. NEVER use new_order (or drop the conversation_id) to recover from an error or a refused checkout — that discards the cart and any pending confirmation. Stay on the same conversation_id and follow the error's instruction instead; new_order is ONLY for the user starting an unrelated order. If it hands out a merchant login link (hosted connect), just reply on the SAME conversation_id once the user finishes (e.g. "done — I logged in") and it verifies the link itself. Logins started here have no pending_id, so the buy_connect / buy_connect_status pair does not apply to them. Call get_instructions FIRST for the current usage guide before your first buy.

NameTypeReqDescription
conversation_idstringThe conversation_id returned by a previous buy call. Pass it to continue the SAME order (keeps the cart + confirmation). Omit to start a new order.
new_orderbooleanStart a fresh shopping conversation instead of continuing the current one. Use when beginning an unrelated order (ignores any conversation_id).
requeststringyesThe natural-language ask or follow-up, e.g. "order a caesar salad from Zuni on DoorDash", "deliver to 123 Main St", or "yes, place the order".
NameTypeReqDescription
conversation_idstringThe conversation id to thread back as conversation_id on the next buy call to continue the SAME order. Present on a successful assistant turn.
messagestringyesThe assistant's conversational turn (it may ask for the delivery address, show the cart + total, confirm, or report a placed order), or an error explanation.
messagesarrayThe same turn split into ordered messages for multi-bubble surfaces (each narration segment, then the final reply/confirmation). `message` is the same content consolidated; clients that show one bubb…
statusstringDiscriminator for the outcome. 'assistant_turn' when the buy loop replied; 'conversation_start_failed' or 'request_failed' on errors.

No examples provided.

buy_connect ~166

Connect a merchant for shopping. For merchants that need a real login (e.g. DoorDash) this opens a secure hosted browser session and returns a URL the user opens to log in; after they finish, call buy_connect_status with the pending_id to confirm. Merchants that need no login (e.g. Agentcard Flights) come back ready immediately. Use this instead of buy_link_merchant for hosted-login merchants. This tool pairs only with buy_connect_status and only tracks logins it started itself; a login link handed out by the conversational `buy` tool has no pending_id and is verified inside that same buy conversation (the user replies there, e.g. "done — I logged in").

NameTypeReqDescription
merchantstringyesmerchant slug (e.g. doordash)
NameTypeReqDescription
loginUrlstringURL the user must open to log in to the merchant. Absent for auto-link merchants.
merchantstringThe merchant slug, present when an auto-link merchant needs no login.
messagestringyesHuman-readable next step.
pendingIdstringSession id to pass to buy_connect_status. Absent for auto-link merchants.
statusstringOutcome: 'pending' (hosted login started), 'ready'/'linked' (auto-link merchant — no login needed), or 'error'.

No examples provided.

buy_connect_status ~145

Check the status of a hosted merchant login started with buy_connect. Returns linking (still in progress — call again in a few seconds), linked (success — the merchant is ready to shop), expired, or error. Pass the merchant and the pending_id from buy_connect. ONLY for logins started by the buy_connect tool: a login link handed out by the conversational `buy` tool has no pending_id — for those, reply to the same `buy` conversation ("done — I logged in") instead of calling this.

NameTypeReqDescription
merchantstringyesmerchant slug (e.g. doordash)
pending_idstringyesThe pending_id returned by buy_connect.
NameTypeReqDescription
cart_carried_overbooleanTrue when a cart built anonymously before linking was moved onto the linked account — re-show it (buy_view_cart) and re-confirm the total before checkout.
merchantstringThe merchant slug, present when linked.
messagestringyesHuman-readable status / next step.
statusstringConnect state: 'linking', 'linked', 'expired', or 'error'.

No examples provided.

buy_list_merchants ~42

List merchants available for agent commerce (Rappi, Good Eggs, DoorDash) and whether this user has linked each one. Link a merchant before shopping it.

Input schema present but exposes no named parameters.

NameTypeReqDescription
countnumberNumber of merchants returned.
merchantsarrayAvailable commerce merchants and this user's link status for each.
messagestringyesHuman-readable merchant list (or an error / empty note).
statusstringOutcome: 'ok', 'empty', or 'error'.

No examples provided.

buy_unlink_merchant ~57

Disconnect a merchant — drops the saved session + link. The user must re-link (e.g. hosted connect) before shopping it again.

NameTypeReqDescription
merchantstringyesMerchant slug to disconnect (e.g. doordash).
NameTypeReqDescription
merchantstringThe merchant slug that was unlinked (or attempted).
messagestringyesHuman-readable unlink outcome.
statusstringOutcome: 'unlinked', 'not_linked', or 'error'.

No examples provided.

check_kyc_document ~50

Check the conversational verification state — use after the user uploads their ID via the browser upload link (or any time you need to re-orient). Returns the current step and the fields still missing.

Input schema present but exposes no named parameters.

NameTypeReqDescription
messagestringyes
missingFieldsarray
nextStepstring|null
uploadUrlstring
verificationUrlstring

No examples provided.

close_card ~196

Permanently close a virtual card. This is irreversible — the card cannot be reopened. Safe to call on an already-closed card (idempotent). The user's rewards card (the card their tokenback redeems onto) is close-protected: closing it returns its balance to the wallet but retires the card number the user may have on file at AI labs, so it requires confirm_rewards_card — set it ONLY after the user explicitly confirms they want the rewards card closed.

NameTypeReqDescription
approval_idstringApproval id from a prior approval_required response, once the user has approved. Only for cards created through ANOTHER app: first call without it (the user is emailed an approve link), then retry wi…
card_idstringyesThe card ID to close
confirm_rewards_cardbooleanRequired to close the rewards card. Only set after the user explicitly confirms; never set it preemptively.
NameTypeReqDescription
approvalIdstringPresent when status is approval_required: pass it back as approval_id after the user approves.
cardIdstringThe ID of the card that was closed.
messagestringyesHuman-readable confirmation that the card was closed.
statusstringOutcome discriminator; always "closed" on success.

No examples provided.

create_card ~1,014

The one card tool: get the user a virtual debit card for a purchase. Cards are live and charged for real when used. For a FIRST-TIME user it starts by putting the user's OWN card in their Agentcard vault (any Visa, Mastercard, Amex, or Discover from any country, no identity verification (KYC), no balance funding): the call returns a secure link (vault_started); send it to the user (they type the card once and lock it with their passkey or master password; Agentcard never sees the number). A vaulted card pays through the buy tool, where the user approves each purchase on their device with their passkey or master password; it never becomes a card number you type, so after vault_started (or vault_ready, when a card is already in the vault) use buy for purchases instead of calling create_card again. If the user specifically needs a card NUMBER, that is an Agentcard funded from their cash balance, which requires KYC the first time: only after the user agrees, call create_card with source "issued". Established users: the saved default decides (get_settings default_payment: their chosen added card, or the wallet balance); with no saved default, an active ADDED card wins, otherwise the cash balance. Per-call overrides: connected_card_id issues against a specific added card, source "issued" forces the cash balance, restart_setup mints a fresh vault link. If the balance is short on the issued path, top up with add_funds. Connections through a company OAuth client have NO card count or amount limits; only first-party personal accounts have per-plan caps. Call get_plan for the limits in effect.

NameTypeReqDescription
amount_centsnumberyesCard funding amount in CENTS, not dollars (minimum 100). 100 = $1.00 and 2500 = $25.00 — a value like 25 would be $0.25. Company-governed connections have no maximum; personal accounts are capped by…
connected_card_idstringMulti-card: issue against a SPECIFIC added card (an id from the user's added cards, see list_added_cards) instead of the newest active one. Omit for the default.
expires_atstringOptional hard expiry for a multi-use card (ISO-8601 with timezone, e.g. "2027-01-01T00:00:00Z"). Must be in the future, at most 365 days out. The card closes automatically when it passes.
funds_sourcestringWhere the card funds come from. OMIT unless instructed: the server applies the right default (company-connected accounts use the company wallet automatically when the company enables it). company_flo…
pending_card_idstringOnly when retrying an approval_pending purchase whose preset has since changed: the cardId from that earlier answer, together with purchase_key. The older approval link is retired once the replacemen…
presetPreset for this card: a template name (ai_labs, weekday_meals, cli_only, daily), comma-separated templates, a saved preset name/id, inline JSON privileges, or { name?, privileges }. Adds restrictions…
purchase_keystringThe purchaseKey from the same approval_pending answer as pending_card_id; the pair proves the retry is for that purchase.
restart_setupbooleanSet true ONLY when the user lost or never received a vault link, it expired (about 15 minutes), or they want to add ANOTHER card. Never needed on the first call or for normal retries. amount_cents is…
scope_presetstringSilent alias for preset 'ai_labs': a multi-use card restricted to AI-lab merchants (OpenAI, Anthropic, Gemini); charges anywhere else are declined at authorization. AI cards earn boosted tokenback on…
sourcestringForce the card to be funded from the user's cash balance (the issued path: KYC + wallet funding) even when they have an added or vaulted card or would otherwise be offered the vault. Use it only afte…
typestringCard behavior. 'single_use' (default) closes after its first approved charge — right for one-off purchases. 'multi_use' stays open across charges until its total limit is spent — right for subscripti…
NameTypeReqDescription
approvalIdstringThe approval request ID to pass to approve_request. Present only when status is "approval_required".
approvalUrlstringThe passkey approval link to send to the user. Present only when status is "approval_pending".
attachUrlstringThe secure link the user opens to finish an older add-card enrollment. Present only when status is "attach_started".
balanceCentsnumberCard balance in cents. Present only when status is "created".
balanceDollarsstringCard balance formatted as USD dollars, e.g. "12.50". Present only when status is "created".
cardIdstringThe new card ID. Present only when status is "created".
cardStatusstringCard status, e.g. "active". Present only when status is "created".
expiresAtstringWhen the link expires (ISO 8601). Present when status is "vault_started" or "attach_started".
expirystringCard expiry (MM/YY). Present only when status is "created".
last4stringLast four digits of the new card. Present only when status is "created".
maxAmountCentsnumberThe issuing rail's per-card ceiling in cents. Present when status is "limit_reached" because the amount exceeded that ceiling; retry with amount_cents at most this value.
messagestringyesHuman-readable result or guidance for the next step.
missingFieldsarrayWhat is missing when status is "user_info_required" (e.g. "termsAccepted", "consent").
pendingCardIdstringThe parked card awaiting the passkey. Present only when status is "approval_pending"; pass it back as pending_card_id on the retry, with purchaseKey as purchase_key.
presetobject|nullPreset summary for the new card, or null when unrestricted. Present when status is "created".
purchaseKeystringThe purchase's key. Present only when status is "approval_pending"; pass it back as purchase_key with pending_card_id.
reasonstringOn "issuing_suggested" (legacy servers only; current servers route every first-time user to the vault instead): why the card could not be added. On "kyc_required": why the previous identity-verificat…
sourcestring"connected" when the card was created against the user's added card. Absent for wallet-funded cards.
statusstringOutcome discriminator: "created" (card issued), "vault_started" (first-time setup: send vaultUrl to the user; once their card is in the vault, purchases go through buy, not create_card), "vault_ready…
vaultCardsnumberHow many cards the user already holds in their vault. Present only when status is "vault_ready".
vaultUrlstringThe secure link the user opens to put their card in their vault. Present only when status is "vault_started".

No examples provided.

create_withdrawal_recipient ~329

Save a bank account as a withdrawal destination for the user's cash balance. Supports US bank accounts (ACH: routing + account number) and international bank accounts (SWIFT wire: IBAN + BIC). Ask the user for their bank details conversationally, then call this once. After saving, use withdraw to request a payout.

NameTypeReqDescription
account_numberstringACH only: US account number (4-17 digits).
account_typestringACH only: account type.
bank_namestringThe recipient bank's name (recommended).
beneficiary_namestringyesThe account holder's full legal name, exactly as the bank knows it.
country_codestringyesTwo-letter country code of the account holder (e.g. 'US', 'DE').
country_specificobjectExtra banking fields some countries require: {"ifsc": "..."} for India, {"clabe": "..."} for Mexico, {"bsb": "..."} for Australia. Required for those countries; the validation error names the missing…
ibanstringInternational only: IBAN (e.g. DE89370400440532013000).
nicknamestringA label for this account (e.g. 'My checking').
routing_numberstringACH only: 9-digit US routing number.
swift_codestringInternational only: 8 or 11 character SWIFT/BIC.
typestringyesach for US bank accounts; international_wire (SWIFT) for everywhere else.
NameTypeReqDescription
messagestringyesHuman-readable result or next step.

No examples provided.

delete_preset ~79

Delete a preset you saved (from save_preset). Refuses built-in template names — there's nothing to delete there. Cards already issued keep whatever rules they have; this only retires the name for future use. Refused while a card still inherits the name as a standing default.

NameTypeReqDescription
namestringyesThe saved preset name to delete.
NameTypeReqDescription
deletedboolean
messagestringyes

No examples provided.

get_balance ~61

The user's cash balance: the money that funds new cards. Provisions the balance account on first use. Users add cash with Apple Pay or Google Pay in USD; funds are held as USDC. (Their wallet, meaning the cards themselves, is list_cards.)

Input schema present but exposes no named parameters.

NameTypeReqDescription
balanceUsdstringSpendable cash balance in USD (string decimal).
confirmingUsdstringDeposit clearing on-chain, not yet spendable (present only mid-deposit).
messagestringyesHuman-readable balance summary.
statusstringBalance account status.

No examples provided.

get_card_balance ~63

The live balance of ONE virtual card (the user's overall cash balance is get_balance). Prefer this over get_card_details when you only need to verify available funds: it is faster and does not expose sensitive card credentials.

NameTypeReqDescription
card_idstringyesThe card ID
NameTypeReqDescription
balanceCentsnumberAvailable balance in cents.
balanceDollarsstringAvailable balance formatted as USD dollars, e.g. "12.50".
cachedbooleanWhether the balance was served from a short-lived cache rather than fetched live.
messagestringyesHuman-readable balance summary.

No examples provided.

get_card_details ~145

Get decrypted PAN, CVV, expiry, and current balance for a specific card. Use this only when you need to fill in a payment form — prefer get_card_balance if you only need the balance. May require human approval before returning credentials. If approval is required, prompt the user and then call approve_request. Card details are encrypted at rest with AES-256-GCM.

NameTypeReqDescription
approval_idstringApproval id from a prior approval_required response, once the user has approved. Only for cards created through ANOTHER app: first call without it (the user is emailed an approve link), then retry wi…
card_idstringyesThe card ID
NameTypeReqDescription
approvalIdstringThe approval request ID to pass to approve_request. Present only when status is "approval_required".
balanceCentsnumberCard balance in cents. Present only when status is "details".
balanceDollarsstringCard balance formatted as USD dollars, e.g. "12.50". Present only when status is "details".
cardIdstringThe card ID.
cardStatusstringCard status, e.g. "active" or "closed". Present only when status is "details".
expirystringCard expiry (MM/YY). Present only when status is "details".
last4stringLast four digits of the card number. Present only when status is "details".
messagestringyesHuman-readable card details (or an approval-required prompt).
statusstringOutcome discriminator: "details" when credentials were returned, "approval_required" when human approval is needed first, "not_accessible" when the card exists outside this connection's scope, "polic…

No examples provided.

get_card_preset ~64

Read a card's preset (spend limits, rate limits, allowed categories/merchants, time windows, and surfaces) as a plain-English summary. A card without a preset is unrestricted.

NameTypeReqDescription
card_idstringyesThe card id (from list_cards).
NameTypeReqDescription
cardIdstring
messagestringyes
presetobject|nullPreset summary, or null when unrestricted.

No examples provided.

get_instructions ~46

Call this FIRST; returns the latest usage guide for shopping with `buy` AND for operating the Agentcard account tools (cards, funding, your own card, KYC, support).

Input schema present but exposes no named parameters.

NameTypeReqDescription
messagestringyesThe latest buy usage guide / instructions text.

No examples provided.

get_kyc_status ~63

Check the user's identity verification (KYC) status. Returns whether they are verified and, if not, the current state plus the conversational next step. Use this to poll after the user does the face scan, or any time create_card reports kyc_required.

Input schema present but exposes no named parameters.

NameTypeReqDescription
messagestringyesHuman-readable status / next step.
missingFieldsarray
nextStepstring|nullConversational next step when the flow is in progress.
reasonstring|nullFailure reason from the verification provider when one exists.
statusstring|nullRaw KYC state: "verified", "pending", "requires_input", "duplicate_identity", "canceled", or null if never started.
verificationUrlstring
verifiedbooleanTrue when identity verification has passed.

No examples provided.

get_plan ~84

Show the user's current subscription plan, card limits, and this month's usage. Call this before create_card when you need the per-card amount cap or remaining monthly quota, or whenever the user asks about their plan, limits, billing, or upgrading. To cancel a paid plan, the gated tool cancel_plan also exists; call it by name even though it isn't in the tools list.

Input schema present but exposes no named parameters.

NameTypeReqDescription
cancelAtPeriodEndbooleanWhether the subscription cancels at the end of the current billing period.
cardsRemainingnumber|nullCards remaining this month; null means unlimited.
cardsThisMonthnumberNumber of cards created this month.
currentPeriodEndstring|nullISO date the current billing period ends, or null.
maxCardAmountCentsnumber|nullThe per-card cap in effect, in cents: the tighter of the plan cap and the issuing rail's own ceiling; null means no per-card cap at all.
maxCardAmountDollarsstring|nullThe per-card cap in effect, formatted as USD dollars, e.g. "500.00"; null means no per-card cap.
maxCardsPerMonthnumber|nullMax cards allowed per month; null means unlimited (connections through a company OAuth client or organization have no card limits).
maxLifetimeOrdersnumber|nullLifetime free-order quota; null means unlimited (paid plans).
messagestringyesHuman-readable plan + usage summary.
ordersPlacednumberOrders placed (counts toward the free-order quota on Free).
planstringRaw plan id, e.g. 'free', 'basic', or 'pro'.
planMaxCardAmountCentsnumber|nullThe personal plan's per-card cap, in cents; null for company-governed connections (no plan cap).
planNamestringDisplay label of the plan, e.g. "Basic ($15/mo)".
railMaxCardAmountCentsnumber|nullThe issuing rail's own per-card ceiling for cards funded from the cash balance (source "issued"), in cents, when the rail this account mints on has one; enforced when such a card is created, not on p…
subscriptionStatusstring|nullStripe subscription status (e.g. 'active', 'past_due'), or null on Free / when unavailable.

No examples provided.

get_rewards ~89

Show the user's tokenback: balance, lifetime earned, and recent activity. Tokenback pays tokens (1 token = 1¢ of credit value) on settled card spend. AI cards (create_card scope_preset: 'ai_labs') earn a boosted rate on AI-lab purchases, and companies can route a share of their earnings to their users as tokenback. Redeem with redeem_rewards.

Input schema present but exposes no named parameters.

NameTypeReqDescription
balanceTokensnumberCurrent token balance (1 token = 1 cent).
lifetimeEarnedTokensnumberTokens earned all-time.
messagestringyesHuman-readable summary.
minRedeemTokensnumberMinimum tokens per redemption.
redeemedTokensnumberTokens redeemed all-time.

No examples provided.

get_settings ~116

View the user's notification preferences (which email alerts they receive), their default payment source (which card or balance agents charge — check it before picking a funding source for them), their default delivery address (the wallet-level shipping address to use when buying physical goods for them — check it before asking them to dictate an address), and authorization settings (whether viewing card details or making transactions requires explicit approval). Authorization settings are read-only here; change the rest with the gated tool update_settings, calling it by name even though it isn't in the tools list.

Input schema present but exposes no named parameters.

NameTypeReqDescription
authorizationobjectAuthorization (approval) settings — read-only.
default_paymentobject|nullThe wallet-level default payment source: { source: 'balance' } or { source: 'connected', connected_card_id }. null = auto (an active added card wins, else the balance).
delivery_addressobject|nullThe wallet-level default delivery address (street/city/state/zip + optional address2/phone/name), or null when unset.
messagestringyesHuman-readable settings summary.
notificationsobjectEmail notification preferences.

No examples provided.

get_wallet_link ~297

The user's hosted wallet, as one shareable URL. Opens their Agentcard wallet in the browser: every card in one place, apply for an Agentcard card (identity verification runs right in the page). Mint it whenever the user needs a browser step (seeing cards, finishing verification when in-chat photos fail) and send them the URL. To ADD the user's own card, pass purpose "add_card": the link then opens their Agentcard vault card form directly (any card, typed once, locked with their passkey or master password, never seen by Agentcard) and works on personal logins too. Pass merchant + amount_cents to open the wallet ON the payment-approval sheet (the user picks a card and approves that exact charge) instead of the card list. Multi-use but short-lived (about 15 minutes — the exact moment is in expiresAt); mint a fresh one when it expires. The wallet link only works for app connections (OAuth).

NameTypeReqDescription
amount_centsintegerAmount in cents. When present, the link opens on the payment-approval sheet for this charge.
merchantstringMerchant name shown on the payment-approval sheet (with amount_cents).
purposestring"wallet" (default) opens the hosted wallet. "add_card" opens the vault card form so the user can put their own card on file; single-use, about 15 minutes.
NameTypeReqDescription
expiresAtstringISO time the link stops working.
kindstringpurpose add_card only: how the vault link signs the user in. "connected" = a one-time code to their own phone or email; "handoff" = directly; "open" = passkey setup or passkey sign-in.
messagestringyesReady-to-send sentence containing the URL.
sandboxbooleanTrue when the connection is in test mode.
urlstringThe hosted wallet URL to share with the user.

No examples provided.

link_account ~237

Link or merge another Agentcard account that belongs to the same person. Use when the user says they already have an account under a DIFFERENT email or phone number — most often after identity verification (KYC) is rejected as a duplicate, which means that person already verified on another account. Two steps: (1) call with { type, identifier } to send a one-time code to that email/phone; (2) call again with the { ticket, code } to verify. If the identifier belongs to a different account, the two accounts are MERGED (the identity-verified account survives and gains the other's email/phone, so both sign in to one account); if no account has it, it is simply added to the current account.

NameTypeReqDescription
codestringStep 2: the one-time code the user received.
identifierstringStep 1: the email address or phone number of the other account to verify.
ticketstringStep 2: the ticket returned by step 1.
typestringStep 1: which kind of identifier the OTHER account uses.
NameTypeReqDescription
messagestringyesHuman-readable result or next step.

No examples provided.

list_added_cards ~107

List the user's ADDED cards (their own Visa/Mastercard cards enrolled via create_card's add-card flow — the funding source that charges their own card), with ids, brand, last4, expiry, and status. The row marked isDefault is what create_card charges when no connected_card_id is given — the user's chosen default card (set with update_settings default_payment), falling back to the newest active one. Not the same as list_cards (the virtual cards Agentcard issues).

Input schema present but exposes no named parameters.

NameTypeReqDescription
attachedCardsarrayAdded-card enrollments, newest first. The row with isDefault true is the default for new cards; none is marked when the default payment is the wallet balance.
countnumberNumber of non-revoked added cards.
messagestringyesHuman-readable list (or an empty-state note).

No examples provided.

list_cards ~161

The user's wallet: every live card they hold, with IDs, last four digits, expiry, balance, and status, plus `vaultCards`: the user's OWN cards stored in their Agentcard vault (display fields only; a vaulted card pays through buy with an approval on the user's device (their passkey or master password) and never exposes a number). Start here to find available cards; if none are returned, call create_card. When the shared wallet is enabled, `wallet` lists every card across all connected apps and companies, each tagged with its source (kind personal/company, the issuing app, and the company where applicable); cards created by another app or company are read-only from this session: get_card_details and close_card will not work on them.

Input schema present but exposes no named parameters.

NameTypeReqDescription
cardsarrayThe user's own virtual cards.
connectedAccountsarrayRead-only cards issued and managed by an organization the user is linked to.
countnumberTotal number of cards across the user's own cards and any connected-account cards.
messagestringyesHuman-readable list of cards (or an empty-state message).
vaultCardsarrayThe user's own cards stored in their Agentcard vault. Display fields only; they pay through buy with an approval on the user's device (their passkey or master password) and never expose a card number.
walletarrayOne-wallet view (present when the shared wallet is enabled): every LIVE card across personal and company sources, each tagged with its provenance. Closed cards are excluded; transactions carry histor…

No examples provided.

list_connections ~59

List the third-party apps the user has connected to their Agentcard account via OAuth (e.g. Kilo), including when each was connected and whether it is still active. Read-only. To revoke an app, call revoke_connection with its clientId.

Input schema present but exposes no named parameters.

NameTypeReqDescription
connectionsarrayThe third-party apps connected to the user's account via OAuth.
countnumberNumber of connected apps.
messagestringyesHuman-readable summary of the connected apps.
statusstringResult status: "no_connections" when none are connected, otherwise "ok".

No examples provided.

list_payment_methods ~90

List the saved payment methods (used only to pay for flight bookings, not for cards or adding funds). Returns each method with its id, brand, last 4 digits, and expiry, and marks the default one. Use setup_payment_method to add a new one. The gated tools set_default_payment_method and remove_payment_method also exist; call them by name even though they aren't in the tools list.

Input schema present but exposes no named parameters.

NameTypeReqDescription
countnumberNumber of saved payment methods.
defaultIdstringThe id of the payment method marked as default, if any.
messagestringyesHuman-readable summary of the saved payment methods.
paymentMethodsarrayThe saved payment methods.
statusstringWhether any payment methods are saved.

No examples provided.

list_pending_approvals ~102

List the user's PENDING approval requests: asks from connected apps (create a card, view full card details, close/pause/resume a card, change a limit) waiting on the user's decision. Surface each one to the user and let THEM decide; after the user answers, resolve with approve_request. NEVER approve or deny on your own — an approval is the user's consent, not yours. Personal sessions only; company-connected sessions have no personal inbox.

Input schema present but exposes no named parameters.

NameTypeReqDescription
approvalsarrayPending, unexpired approval requests, newest first. Each is waiting on the user's decision.
countnumberNumber of pending approvals.
messagestringyesHuman-readable list of pending approvals (or an empty-state note).
statusstringPresent only when the list is unavailable: "personal_surface_only" for company-connected sessions.

No examples provided.

list_presets ~52

List every preset you can use by name: the built-in templates (ai_labs, weekday_meals, cli_only, daily) plus any you've saved yourself, each with a plain-English summary of its rules.

Input schema present but exposes no named parameters.

NameTypeReqDescription
messagestringyes
presetsarray

No examples provided.

list_transactions ~182

Transactions with amount, merchant, status, and timestamps. Pass card_id for one card's transactions; OMIT it for every card in the account (newest first, each row tagged with its card). Use limit and status to filter. The gated views list_all_transactions and list_transactions_by_payment_method also exist; call them by name even though they aren't in the tools list.

NameTypeReqDescription
card_idstringA card ID for that card's transactions; omit for all cards in the account.
limitnumberMax number of transactions to return (default 20)
offsetnumberSkip this many (all-cards view pagination; ignored for a single card).
statusstringFilter by transaction status (e.g. PENDING, SETTLED, DECLINED, REVERSED, EXPIRED, REFUNDED)
NameTypeReqDescription
countnumberNumber of transactions returned.
messagestringyesHuman-readable list of transactions (or a "no transactions" note).
transactionsarrayThe transactions for the card, newest first.

No examples provided.

list_withdrawal_recipients ~63

List the user's saved bank accounts for withdrawals, masked (bank name and last four only). Use a recipient's id as recipient_id with withdraw. If the list is empty, collect the user's bank details and call create_withdrawal_recipient first.

Input schema present but exposes no named parameters.

NameTypeReqDescription
countnumberNumber of saved bank destinations.
messagestringyesHuman-readable list (or an empty-state note).
recipientsarraySaved bank destinations, masked.

No examples provided.

manage_subscription ~341

Manage a recurring meal/grocery SUBSCRIPTION (e.g. Locale) — NOT a one-time purchase, and no payment is taken (the subscription auto-bills the card on file at the merchant). action: 'menu_search' (browse the recurring menu; items flagged inPlan are covered by the plan), 'get_skip_dates' (list skipped/paused deliveries), 'skip'/'unskip' (one upcoming delivery date), 'set_skip_dates' (replace the full skip set; [] resumes all), 'update_setting' (change a setting). Locale settings: subscription_size (meals, e.g. 8), calorie_preference (low_calorie|both|moderate), diets (array), longevity_allergens (array), ingredient_allergies (array), default_window ('9am - 6pm'|'3pm - 7pm'|'9am - 12pm'), delivery_instructions (text). Link the merchant first.

NameTypeReqDescription
actionstringyesthe management action
datestringskip/unskip: one ISO delivery date (YYYY-MM-DD)
datesarrayset_skip_dates: FULL set of ISO dates to skip ([] resumes all)
limitnumbermenu_search: max items
merchantstringyesmerchant slug (e.g. locale)
querystringmenu_search: term over the recurring menu (e.g. 'salmon'); '' lists everything
settingstringupdate_setting: the setting key (see description)
valueupdate_setting: the new value (number, string, or array of strings)
NameTypeReqDescription
messagestringyesHuman-readable result or next step.

No examples provided.

name_card ~212

Tell the vault which card product one of the user's own stored cards is (e.g. "Chase Sapphire Preferred", "Amex Gold"), so smart purchases can rank it. Takes a vault card id (a `vaultCards` row from list_cards) and the product name as the user says it; the closest match is saved and echoed back. Confirm with the user when the match is not obviously right. Pass clear_product to forget the name, or smart_excluded to keep a card out of the ranking without removing it.

NameTypeReqDescription
card_idstringyesThe vault card id (from list_cards → vaultCards).
clear_productbooleantrue = forget the product name. Do not combine with product.
productstringThe card product as the user says it, e.g. "Chase Sapphire Preferred" or "Amex Gold". Four characters minimum.
smart_excludedbooleantrue = leave this card out of smart purchases; false = include it again.
NameTypeReqDescription
matchesarrayOn no_match or an ambiguous name: the closest products found, to offer the user.
messagestringyesWhat was saved.
product_keystring|nullThe saved product key.
product_namestring|nullThe saved product name.
statusstringyes"named" | "cleared" | "updated" | "no_match" | "ambiguous" (several products match; nothing saved, ask the user) | "noop".

No examples provided.

pause_card ~140

Pause a multi-use card: temporarily blocks ALL new charges (reversible — use resume_card to unblock). Right for "stop this subscription for now" or a card the user suspects is compromised but is not sure. Only multi-use cards can be paused; single-use cards close after one charge and cannot be paused.

NameTypeReqDescription
approval_idstringApproval id from a prior approval_required response, once the user has approved. Only for cards created through ANOTHER app: first call without it (the user is emailed an approve link), then retry wi…
card_idstringyesThe card ID to pause (from list_cards or create_card).
NameTypeReqDescription
cardIdstringThe card ID.
messagestringyesHuman-readable result.
statusstring"paused" on success; an error discriminator otherwise (e.g. "not_multi_use", "card_not_updatable").

No examples provided.

read_support_chat ~29

Read the message history of a support conversation

NameTypeReqDescription
conversation_idstringyesThe conversation ID
NameTypeReqDescription
countnumberNumber of messages returned.
messagestringyesHuman-readable rendering of the conversation history.
messagesarrayThe messages in the conversation, oldest first.
statusstringOutcome of the read: 'empty' when there are no messages yet, 'ok' when messages were returned.

No examples provided.

recommend_card ~200

Ask the vault which of the user's own stored cards earns the most for a purchase (smart purchases). Pass the merchant name, its website when you know it, and the amount. Returns the card id to use as card_id at checkout, the reason in plain words, and the runners-up. null when smart purchases is off for this account, no stored card has been named yet (see name_card), or nothing could be said; then pay as you would have. Never a card number.

NameTypeReqDescription
amount_centsnumberOrder total in cents, when known.
currencystringISO currency code, default usd. Non-USD purchases account for foreign transaction fees.
merchantstringyesThe merchant as the user would see it, e.g. "DoorDash".
merchant_urlstringThe merchant's website or checkout origin, e.g. https://www.doordash.com. Improves the category match.
NameTypeReqDescription
alternativesarrayOther stored cards with their estimated value in cents and reason.
card_idstring|nullThe vault card to pay with (pass as card_id at checkout), or null.
categorystring|nullThe spend category the merchant resolved to.
messagestringyesHuman-readable pick and reason.
reasonstring|nullWhy, in one or two sentences the user can be told verbatim.

No examples provided.

redeem_code ~133

Redeem a promo code that adds money to the user's cash balance. Each code works once per user; the credit lands in the balance and becomes spendable within a minute or two. Some codes hold the money until the user verifies their identity — the claim still locks the code to this user instantly, and the credit lands automatically once KYC is approved (start_kyc begins verification). The gated tool list_codes shows the user's code history; call it by name even though it isn't in the tools list.

NameTypeReqDescription
codestringyesThe promo code exactly as the user provided it (case and dashes are forgiven).
NameTypeReqDescription
messagestringyesHuman-readable result or next step.

No examples provided.

redeem_rewards ~117

Redeem tokenback: the tokens' cash value (1 token = 1¢) lands on the user's rewards card as spending power. The rewards card is permanent and locked to AI-lab merchants (OpenAI, Anthropic, Gemini) — created on first redemption, topped up after. Check get_rewards first for the balance and the minimum. Ask the user before redeeming.

NameTypeReqDescription
tokensnumberyesHow many tokens to redeem (1 token = 1 cent, so 500 tokens = $5.00 of wallet credit).
NameTypeReqDescription
amountCentsnumberWallet credit in cents. Present when status is "redeemed".
deliveredCardIdstringRewards card the value landed on, when delivery completed inline. Absent = the value sits as wallet credit (it reaches the rewards card within a few minutes when delivery is enabled).
deliveredCardLast4stringLast 4 digits of the rewards card, when delivered inline.
messagestringyesHuman-readable result.
redemptionIdstringThe redemption ID. Present when status is "redeemed".
statusstring"redeemed" on success; an error discriminator otherwise (e.g. "below_minimum", "insufficient_tokens", "redemption_in_progress").

No examples provided.

remove_added_card ~103

Remove (unenroll) one of the user's added cards. Irreversible for that enrollment: any virtual cards created against it are closed first, then the card is unenrolled at the network. ALWAYS confirm with the user before calling. Get ids from list_added_cards. The user can add the same card again later (create_card with restart_setup: true).

NameTypeReqDescription
attached_card_idstringyesThe id of the added card to remove (from list_added_cards).
NameTypeReqDescription
closedCardsnumberHow many virtual cards created against it were closed.
idstringThe id of the removed card.
messagestringyesHuman-readable confirmation or guidance.
statusstring"revoked" on success.

No examples provided.

resume_card ~89

Resume a paused multi-use card so it accepts charges again. The inverse of pause_card.

NameTypeReqDescription
approval_idstringApproval id from a prior approval_required response, once the user has approved. Only for cards created through ANOTHER app: first call without it (the user is emailed an approve link), then retry wi…
card_idstringyesThe paused card ID to resume.
NameTypeReqDescription
cardIdstringThe card ID.
messagestringyesHuman-readable result.
statusstring"active" on success; an error discriminator otherwise (e.g. "card_not_paused").

No examples provided.

revoke_connection ~73

Revoke a third-party app's access to the user's Agentcard account. Disconnects the app and invalidates its OAuth tokens; it must reconnect via OAuth to regain access. Pass the clientId shown by list_connections.

NameTypeReqDescription
client_idstringyesThe OAuth client ID of the app to revoke (from list_connections).
NameTypeReqDescription
clientIdstringThe client ID that was revoked.
messagestringyesHuman-readable outcome.
revokednumberNumber of OAuth tokens that were revoked.
statusstringResult status: "revoked" when tokens were invalidated, "not_connected" when the app had no active access.

No examples provided.

save_preset ~644

Save your own preset — a named set of rules (spend caps, category/merchant/place/currency/day/hour/program restrictions) you can reuse by name in set_card_preset or create_card. Saving under a name you already used adds a new version: cards already using the old one keep it, new ones get the update. Pick a name other than the built-ins (ai_labs, weekday_meals, cli_only, daily). Pass either the rule fields below or a raw `privileges` array.

NameTypeReqDescription
categoriesstringComma-separated spend categories to allow, e.g. "meals,groceries" (meals, groceries, travel, software, ai, wellness, retail).
currenciesstringComma-separated purchase currencies to allow: ISO 4217 codes or common names, e.g. "usd,eur" or "dollars,euros,pounds,yen". In strict mode a purchase in another currency is refused at checkout and a…
modestringWhat the preset does when a purchase breaks any of its rules: "strict" refuses it (the default), "watch" lets it through and tells the user once.
namestringyesA name for this preset, e.g. "meals-only".
only_daysstringComma-separated days to allow, e.g. "mon,tue,wed" or "weekdays"/"weekends".
only_fromstringComma-separated callers to allow, e.g. "cli,mcp" (cli, mcp, api, browser).
only_hoursstringAn hour range to allow, e.g. "9-17" (24-hour clock; defaults to UTC without timezone).
only_instringComma-separated places to allow charges from: a country ("US", "Canada"), a region ("europe", "eu", "north-america", "latin-america", "apac"), or a US state ("California", "US-CA"). A region expands…
only_merchantsstringComma-separated merchant name patterns to allow, e.g. "openai,anthropic".
per_daynumberSpend cap per rolling 24 hours, in US dollars.
per_monthnumberSpend cap per rolling 30 days, in US dollars.
per_weeknumberSpend cap per rolling 7 days, in US dollars.
privilegesarrayAdvanced: raw privilege objects instead of the rule fields above.
timezonestringIANA timezone for only_days/only_hours (default UTC), e.g. "America/Los_Angeles". Always shown in summaries.
totalnumberLifetime spend cap, in US dollars.
NameTypeReqDescription
messagestringyes
presetobject|null

No examples provided.

send_support_message ~38

Send a message in an existing support conversation

NameTypeReqDescription
conversation_idstringyesThe conversation ID
messagestringyesYour message
NameTypeReqDescription
conversationIdstringThe ID of the conversation the message was sent to.
messagestringyesHuman-readable confirmation that the message was sent.

No examples provided.

set_card_preset ~184

Update a card's preset. Pass a template name (ai_labs, weekday_meals, cli_only, daily), a saved preset name (from list_presets), a comma-separated template list, or inline JSON / { name, privileges }. Pass null or "" to clear the card's preset (Agentcard-side checks stop; any limit already on the card network stays). Edits create a new version. The response reports what was applied on Agentcard vs what was updated on the card's spend limit, and whether the change needs a new card.

NameTypeReqDescription
card_idstringyesThe card id (from list_cards).
presetyesTemplate name (ai_labs, weekday_meals, cli_only, daily), comma-separated templates, inline JSON privileges, or { name?, privileges }. Pass null or "" with card_id to clear that card's preset.
NameTypeReqDescription
agentcardOnlyarray
messagestringyes
messagesarray
needsNewCardboolean
policyIdstring
policyVersionnumber
presetobject|null
pushedarray
summarystring

No examples provided.

setup_payment_method ~78

Save a payment method used ONLY to pay for flight bookings (the fare is charged to it via a hold at booking; no virtual card is created for flights). It does NOT fund cards or the cash balance — cards are funded from the balance (see add_funds). Returns a secure checkout URL the user must open to save their card details.

Input schema present but exposes no named parameters.

NameTypeReqDescription
checkoutUrlstringSecure Stripe checkout URL the user must open to save their payment method.
messagestringyesHuman-readable summary of the result.
stripeSessionIdstringIdentifier of the Stripe Checkout session created for the setup.

No examples provided.

Common questions

What is the sh.agentcard/agentcard MCP server?

sh.agentcard/agentcard is an MCP server listed in the public MCP registry as sh.agentcard/agentcard. Prepaid virtual cards for AI agents: one-time cards, spend caps, human approvals. This page covers its hosted endpoint (https://mcp.agentcard.sh/mcp).

Is the sh.agentcard/agentcard MCP server safe to use?

sh.agentcard/agentcard scores 90 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the sh.agentcard/agentcard MCP server expose?

sh.agentcard/agentcard exposes 58 tools: buy, surprise_me, get_instructions, whoami, list_cards, and 53 more. Their descriptions and schemas cost roughly 10,270 tokens of context every time the server is loaded.

Does the sh.agentcard/agentcard MCP server require authentication?

Yes. sh.agentcard/agentcard asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the sh.agentcard/agentcard MCP server still maintained?

sh.agentcard/agentcard is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.