Skip to content

agentcard MCP server

sh.agentcard/agentcardagentcard.shstreamable-httpv1.0.0Scanned

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

55 tools: 7 can delete or cancel things, 2 do something that can't be undone, 28 change things and 18 only read.

Tools: 7 delete, 2 irreversible, 28 write, 18 read.
  • Reads private data · 4
  • Reads text others write · 11
  • Can send data out · 3
  • 6 findings

Tools listed without sign-in. Remote posture

With Anlyon

7 tools here can delete or cancel things and 2 do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the agentcard MCP server can do

The agentcard MCP server is published by agentcard.sh, a domain the MCP Registry verified. It has 55 tools. It can delete or cancel things (7 tools: buy, close_card, delete_preset, remove_added_card and 3 more), do things that cannot be undone, such as sending, paying or publishing (send_support_message and start_phone_verification) and create or change data (28 tools: surprise_me, get_instructions, create_card, set_card_preset and 24 more). 18 tools only read.

4 tools read private data (whoami, list_cards, read_support_chat and 1 more); 11 tools bring in text other people can write (buy, surprise_me, whoami and 8 more); 3 tools can send data out of your system (send_support_message, submit_user_info and submit_kyc_fields). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 6 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 19, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

55 tools

Deletes or cancels 7Claude Code: deny
  • buyShop and check out, in natural language, across the merchants the user has linked (DoorDash, etc.).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Buy
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • close_cardPermanently close a virtual card.No findings

    Why it is in this group

    • The name "close_card" says "close": a word for a change.
    • The description says "irreversible".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Close Card
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • delete_presetDelete a preset you saved (from save_preset).No findings

    Why it is in this group

    • The name "delete_preset" says "delete": a word for removing or ending something.
    Description, as the server wrote it
    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.
  • remove_added_cardRemove (unenroll) one of the user's added cards.No findings

    Why it is in this group

    • The name "remove_added_card" says "remove": a word for removing or ending something.
    • The description says "Irreversible".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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).

    Annotations the server declares

    • title: Remove Added Card
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • revoke_connectionRevoke a third-party app's access to the user's Agentcard account.No findings

    Why it is in this group

    • The name "revoke_connection" says "revoke": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Revoke Connected App
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Can't be undone 2Claude Code: ask
  • send_support_messageSend a message in an existing support conversationCan send data outNo findings

    Why it is in this group

    • The name "send_support_message" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_support_message" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a message in an existing support conversation

    Annotations the server declares

    • title: Send Support Message
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • start_phone_verificationSend (or re-send) the user's one-time funding verification code (the provider verifies the phone on the user's Agentcard identity, valid 60 days).No findings

    Why it is in this group

    • The name "start_phone_verification" says "start": a word for a change.
    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    Description, as the server wrote it
    Send (or re-send) the user's one-time funding verification code (the provider verifies the phone on the user's Agentcard identity, valid 60 days). add_funds already sends this code automatically when verification is needed — call this tool only to RE-send when the code never arrived (any unexpired code still works; sends are rate-limited). Returns the masked destination (text or email) and whether a code was sent; if the phone is already verified it says so and you go straight to add_funds. After the user reads back the code, call verify_phone.

    Annotations the server declares

    • title: Start Phone Verification
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 28Claude Code: ask
  • add_fundsGenerate a secure checkout link the user opens to add cash to their own balance (the money that funds new cards) via Apple Pay, Google Pay, or a bank transfer (ACH or wire from a U…1 finding

    Why it is in this group

    • The name "add_funds" says "add": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...method; you never see or handle payment credentials. If a one-time phone verification is ne..."

      What this check looks for
    Description, as the server wrote it
    Generate a secure checkout link the user opens to add cash to their own balance (the money that funds new cards) via Apple Pay, Google Pay, or a bank transfer (ACH or wire from a US bank account), 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.

    Annotations the server declares

    • title: Add Funds
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • allow_card_merchantRemember 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • approve_requestResolve a pending approval request (approve or deny) once the USER has decided.No findings

    Why it is in this group

    • The name "approve_request" says "approve": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Approve Request
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • buy_connectConnect a merchant for shopping.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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").

    Annotations the server declares

    • title: Connect Merchant (Hosted Login)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • check_kyc_documentCheck the conversational verification state — use after the user uploads their ID via the browser upload link (or any time you need to re-orient).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Check ID Document Status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • create_cardThe one card tool: get the user a virtual debit card for a purchase.No findings

    Why it is in this group

    • The name "create_card" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create Card
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • get_balanceThe user's cash balance: the money that funds new cards.1 finding

    Why it is in this group

    • The name "get_balance" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "get_balance" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_balance" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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.)

    Annotations the server declares

    • title: Get Cash Balance
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_instructionsCall 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).1 finding

    Why it is in this group

    • The name "get_instructions" says "get": a word for reading.
    • The description's first verb is "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "get_instructions" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_instructions" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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).

    Annotations the server declares

    • title: Get Buy Instructions
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • manage_subscriptionManage a recurring meal/grocery SUBSCRIPTION (e.g.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Manage Subscription
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • name_cardTell the vault which card product one of the user's own stored cards is (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Name Card
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • pause_cardPause a multi-use card: temporarily blocks ALL new charges (reversible — use resume_card to unblock).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Pause Card
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • recommend_cardAsk the vault which of the user's own stored cards earns the most for a purchase (smart purchases).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Recommend Card
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • redeem_codeRedeem a promo code that adds money to the user's cash balance.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Redeem Promo Code
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • redeem_rewardsRedeem tokenback: the tokens' cash value (1 token = 1¢) lands on the user's rewards card as spending power.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Redeem Rewards
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • resume_cardResume a paused multi-use card so it accepts charges again.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Resume a paused multi-use card so it accepts charges again. The inverse of pause_card.

    Annotations the server declares

    • title: Resume Card
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • save_presetSave 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.No findings

    Why it is in this group

    • The name "save_preset" says "save": a word for a change.
    Description, as the server wrote it
    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.
  • set_card_presetUpdate a card's preset.No findings

    Why it is in this group

    • The name "set_card_preset" says "set": a word for a change.
    Description, as the server wrote it
    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.
  • setup_payment_methodSave 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).No findings

    Why it is in this group

    • The description's first verb is "save": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Setup Payment Method
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • start_kycBegin (or resume) identity verification.No findings

    Why it is in this group

    • The name "start_kyc" says "start": a word for a change.
    Description, as the server wrote it
    Begin (or resume) identity verification. Verification is CONVERSATIONAL: it starts with a photo of the user's government ID — the backend reads the printed details automatically and the user confirms every value. Only fields the ID does not carry are asked (like the SSN for US documents, or the national ID number for non-US ones); occupation/income questions are never asked. The only browser step is a short face scan at the end. Relay each step to the user as ONE SHORT message (one or two sentences — the current ask only, never the whole flow, never an unrequested link). Returns the next step, ID-photo upload options, and (for legacy hosted-flow accounts) a hosted verification URL instead.

    Annotations the server declares

    • title: Start Identity Verification
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • start_support_chatStart a new support conversation and send the first messageNo findings

    Why it is in this group

    • The name "start_support_chat" says "start": a word for a change.
    Description, as the server wrote it
    Start a new support conversation and send the first message

    Annotations the server declares

    • title: Start Support Chat
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • submit_kyc_documentSubmit the user's ID photo for identity verification.No findings

    Why it is in this group

    • The name "submit_kyc_document" says "submit": a word for a change.
    Description, as the server wrote it
    Submit the user's ID photo for identity verification. Ways in: (a) image data you hold programmatically (e.g. the user sent the photo in this chat and your platform exposes its bytes) — pass front_base64 (and back_base64 for a license back; its barcode reads most accurately); (b) local (stdio) mode — pass file_path/back_file_path and the file is read from disk; (c) neither — you get a secure upload link to hand the user. Do NOT ask the user what kind of document it is or where it was issued — the type and country are detected automatically from the photo; only relay a question if the result says the type could not be determined. Returns the fields read off the document — SHOW THEM TO THE USER for confirmation before continuing — plus whatever is still missing. If the result says NO identity details could be read, the image did not read as an ID at all: never insist to the user that it was their ID. Supported: JPEG/PNG/WebP up to 12MB (convert HEIC or HEIF photos first).

    Annotations the server declares

    • title: Submit ID Document
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • submit_kyc_fieldsSubmit identity fields for verification: the ones the ID photo didn't carry (listed by missingFields — the tax/ID number always has to be asked since IDs don't print it; call it "S…Can send data outNo findings

    Why it is in this group

    • The name "submit_kyc_fields" says "submit": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.phone_number): what the tool writes goes there.
    Description, as the server wrote it
    Submit identity fields for verification: the ones the ID photo didn't carry (listed by missingFields — the tax/ID number always has to be asked since IDs don't print it; call it "SSN" only for US documents and "national ID number" otherwise), corrections to extracted values the user flagged, and the User Agreements acceptance (agreements_accepted, after presenting each agreement verbatim). That number is forwarded directly to the verification provider and never stored by Agentcard. NEVER ask about occupation, income, spending volume, or account purpose — those are filled automatically and must not be asked.

    Annotations the server declares

    • title: Submit KYC Fields
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • submit_user_infoSubmit the user's phone number and terms acceptance for a virtual card.Can send data outNo findings

    Why it is in this group

    • The name "submit_user_info" says "submit": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.phone_number): what the tool writes goes there.
    Description, as the server wrote it
    Submit the user's phone number and terms acceptance for a virtual card. Call this after create_card returns user_info_required. Do NOT ask the user for occupation, income, or account purpose — those are never asked. Identity fields (name, date of birth, SSN / national ID, address) belong to the KYC flow: create_card tells you whether it runs conversationally (start_kyc → ID photo → face scan) or via a hosted verification_url. After phone + terms are saved, retry create_card.

    Annotations the server declares

    • title: Submit User Info
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • surprise_meBuy the user something totally unexpected and very silly/stupid-fun under a small dollar cap (default $10, hard max $25).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Buy the user something totally unexpected and very silly/stupid-fun under a small dollar cap (default $10, hard max $25). Great when the user cannot decide what to order (from DoorDash etc.) or just wants a fun surprise. It kicks off a shopping conversation that FIRST brainstorms deliberately stupid ideas, picks ONE genuinely unexpected item, builds the cart, and shows the item + exact total. It NEVER checks out by itself: the reply includes a conversation_id — relay the user's explicit confirmation ("yes, place it") through the `buy` tool on that SAME conversation_id, exactly like a normal order. Each surprise_me call starts a fresh surprise; use `buy` for all follow-ups (answers, tweaks, the confirmation).

    Annotations the server declares

    • title: Surprise Me
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • update_card_limitChange a multi-use card's total spending limit.No findings

    Why it is in this group

    • The name "update_card_limit" says "update": a word for a change.
    Description, as the server wrote it
    Change a multi-use card's total spending limit. Raising it reserves the extra amount from the user's cash balance (top up with add_funds if short); lowering it frees the difference, but the new limit can never go below what the card has already spent. Single-use cards cannot be resized.

    Annotations the server declares

    • title: Update Card Limit
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • upgrade_planStart a paid-plan upgrade.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "start": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Start a paid-plan upgrade. Choose the target plan: 'basic' ($15/mo — 15 cards/month, up to $500 per card) or 'pro' ($100/mo — 50 cards/month, up to $1,000 per card). Defaults to 'basic' if omitted. Returns a Stripe Checkout URL the user must open in their browser to complete payment. After they finish checkout, the plan updates automatically; verify with get_plan. Use only when the user explicitly wants to upgrade. To cancel a paid plan instead, the gated tool cancel_plan also exists; call it by name even though it isn't in the tools list.

    Annotations the server declares

    • title: Upgrade Plan
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • verify_phoneCheck the one-time code the user received from start_phone_verification.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    Check the one-time code the user received from start_phone_verification. On success the balance is unlocked for funding (the verification stays fresh for 60 days) — call add_funds next. A wrong or expired code returns a recoverable status so you can ask the user to re-check it, or call start_phone_verification to resend.

    Annotations the server declares

    • title: Verify Phone
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 18Show 18 read-only tools
  • buy_connect_statusCheck the status of a hosted merchant login started with buy_connect.Reads text others writeNo findings

    Why it is in this group

    • The name "buy_connect_status" says "status": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Connect Status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • buy_list_merchantsList where Agentcard shops.No findings

    Why it is in this group

    • The name "buy_list_merchants" says "list": a word for reading.
    Description, as the server wrote it
    List where Agentcard shops. With no arguments: the merchants that use an account (DoorDash, flights, the retail stores) and whether this user has linked each, plus how many online stores Agentcard buys from with no account. To check one store, pass `query` with its name or domain (Nike, nordstrom.com): the search covers both kinds. An online store needs no link: ask buy for the product and name the store.

    Annotations the server declares

    • title: List Merchants
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_card_balanceThe live balance of ONE virtual card (the user's overall cash balance is get_balance).1 finding

    Why it is in this group

    • The name "get_card_balance" says "get": a word for reading.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ster and does not expose sensitive card credentials."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Check Card Balance
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_card_detailsGet decrypted PAN, CVV, expiry, and current balance for a specific card.1 finding

    Why it is in this group

    • The name "get_card_details" says "get": a word for reading.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...require human approval before returning credentials. If approval is required, prompt the us..."

      What this check looks for
    Description, as the server wrote it
    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. Agentcard never stores an issued card's number or CVV; each call fetches them again.

    Annotations the server declares

    • title: Get Card Details
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_card_presetRead a card's preset (spend limits, rate limits, allowed categories/merchants, time windows, and surfaces) as a plain-English summary.No findings

    Why it is in this group

    • The name "get_card_preset" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • get_kyc_statusCheck the user's identity verification (KYC) status.No findings

    Why it is in this group

    • The name "get_kyc_status" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get KYC Status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_planShow the user's current subscription plan, card limits, and this month's usage.No findings

    Why it is in this group

    • The name "get_plan" says "get": a word for reading.
    Description, as the server wrote it
    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, and ALWAYS before creating a multi-use card: multi-use cards are a paid-plan feature, so maxActiveMultiUseCards is 0 on Free and the mint is refused. Also call it 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.

    Annotations the server declares

    • title: Get Plan & Usage
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_rewardsShow the user's tokenback: balance, lifetime earned, and recent activity.No findings

    Why it is in this group

    • The name "get_rewards" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get Rewards
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_settingsView 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 so…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_settings" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "view" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "view" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get Settings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_added_cardsList 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, exp…No findings

    Why it is in this group

    • The name "list_added_cards" says "list": a word for reading.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • title: List Added Cards
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_cardsThe 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 (disp…Reads private dataNo findings

    Why it is in this group

    • The name "list_cards" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "vault": it reads secrets.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List Cards
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_connectionsList the third-party apps the user has connected to their Agentcard account via OAuth (e.g.No findings

    Why it is in this group

    • The name "list_connections" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List Connected Apps
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_payment_methodsList the saved payment methods (used only to pay for flight bookings, not for cards or adding funds).No findings

    Why it is in this group

    • The name "list_payment_methods" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List Payment Methods
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_pending_approvalsList 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 decisio…No findings

    Why it is in this group

    • The name "list_pending_approvals" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List Pending Approvals
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_presetsList 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 rul…No findings

    Why it is in this group

    • The name "list_presets" says "list": a word for reading.
    Description, as the server wrote it
    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.
  • list_transactionsTransactions with amount, merchant, status, and timestamps.No findings

    Why it is in this group

    • The name "list_transactions" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List Transactions
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • read_support_chatRead the message history of a support conversationReads private dataReads text others writeNo findings

    Why it is in this group

    • The name "read_support_chat" says "read": a word for reading.

    What it can reach

    • private-dataThe name "read_support_chat" says "read" and "chat": it reads messages.
    • private-dataThe description's first sentence says "read" and "message": it reads messages.
    • untrusted-inputThe name "read_support_chat" says "read" and "chat": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Read the message history of a support conversation

    Annotations the server declares

    • title: Read Support Chat
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • whoamiShow who you are operating as: the authenticated AgentCard account's email, user id, name, plan, KYC + account status, member-since date, and how this session is connected (persona…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "show" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "show" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Show who you are operating as: the authenticated AgentCard account's email, user id, name, plan, KYC + account status, member-since date, and how this session is connected (personal login vs a third-party OAuth app connection, with the app name). Call this when the user asks "who am I" / "which account is this", or before money-moving actions when you need to confirm the account. Read-only. KYC shown here is the stored snapshot — use get_kyc_status when you need the live, provider-checked state.

    Annotations the server declares

    • title: Who Am I
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

132 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 outbound tools breaks every one.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write11
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agentcard__send_support_message",
      "mcp__agentcard__submit_kyc_fields",
      "mcp__agentcard__submit_user_info"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:18 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
37
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.agentcard.sh/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.agentcard.sh/
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 37 tools that change things (7 destructive, 2 irreversible, 28 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.agentcard.sh/mcp: tools/list returned 55 tools to an anonymous client, including buy (destructive), close_card (destructive), delete_preset (destructive), remove_added_card (destructive), revoke_connection (destructive) and 32 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

3 warn3 info
  • The server marks "get_instructions" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_instructions" says "get": a word for reading.

    What this check looks for
  • The server marks "get_wallet_link" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_wallet_link" says "get": a word for reading.

    What this check looks for
  • The server marks "get_balance" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_balance" says "get": a word for reading.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...require human approval before returning credentials. If approval is required, prompt the us..."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...ster and does not expose sensitive card credentials."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...method; you never see or handle payment credentials. If a one-time phone verification is ne..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentcard https://mcp.agentcard.sh/mcp
claude mcp add --transport http agentcard https://mcp.agentcard.sh/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": [
      "mcp__agentcard__whoami",
      "mcp__agentcard__list_cards",
      "mcp__agentcard__get_card_details",
      "mcp__agentcard__get_card_balance",
      "mcp__agentcard__get_card_preset",
      "mcp__agentcard__list_presets",
      "mcp__agentcard__list_added_cards",
      "mcp__agentcard__get_rewards",
      "mcp__agentcard__read_support_chat",
      "mcp__agentcard__list_pending_approvals",
      "mcp__agentcard__get_kyc_status",
      "mcp__agentcard__list_transactions",
      "mcp__agentcard__get_plan",
      "mcp__agentcard__list_payment_methods",
      "mcp__agentcard__list_connections",
      "mcp__agentcard__get_settings",
      "mcp__agentcard__buy_list_merchants",
      "mcp__agentcard__buy_connect_status"
    ],
    "ask": [
      "mcp__agentcard__surprise_me",
      "mcp__agentcard__get_instructions",
      "mcp__agentcard__create_card",
      "mcp__agentcard__set_card_preset",
      "mcp__agentcard__allow_card_merchant",
      "mcp__agentcard__save_preset",
      "mcp__agentcard__get_wallet_link",
      "mcp__agentcard__pause_card",
      "mcp__agentcard__resume_card",
      "mcp__agentcard__update_card_limit",
      "mcp__agentcard__redeem_rewards",
      "mcp__agentcard__recommend_card",
      "mcp__agentcard__name_card",
      "mcp__agentcard__start_support_chat",
      "mcp__agentcard__send_support_message",
      "mcp__agentcard__approve_request",
      "mcp__agentcard__submit_user_info",
      "mcp__agentcard__start_kyc",
      "mcp__agentcard__submit_kyc_document",
      "mcp__agentcard__check_kyc_document",
      "mcp__agentcard__submit_kyc_fields",
      "mcp__agentcard__setup_payment_method",
      "mcp__agentcard__get_balance",
      "mcp__agentcard__add_funds",
      "mcp__agentcard__start_phone_verification",
      "mcp__agentcard__verify_phone",
      "mcp__agentcard__redeem_code",
      "mcp__agentcard__upgrade_plan",
      "mcp__agentcard__buy_connect",
      "mcp__agentcard__manage_subscription"
    ],
    "deny": [
      "mcp__agentcard__buy",
      "mcp__agentcard__close_card",
      "mcp__agentcard__delete_preset",
      "mcp__agentcard__remove_added_card",
      "mcp__agentcard__revoke_connection",
      "mcp__agentcard__link_account",
      "mcp__agentcard__buy_unlink_merchant"
    ]
  }
}

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 agentcard. Review it before you use it.

Capability tags behind 15 rules
  • mcp__agentcard__buy untrusted-input
  • mcp__agentcard__surprise_me untrusted-input
  • mcp__agentcard__whoami private-data, untrusted-input
  • mcp__agentcard__list_cards private-data
  • mcp__agentcard__get_wallet_link untrusted-input
  • mcp__agentcard__send_support_message outbound
  • mcp__agentcard__read_support_chat private-data, untrusted-input
  • mcp__agentcard__submit_user_info outbound
  • mcp__agentcard__submit_kyc_fields outbound
  • mcp__agentcard__upgrade_plan untrusted-input
  • mcp__agentcard__get_settings private-data, untrusted-input
  • mcp__agentcard__buy_unlink_merchant untrusted-input
  • mcp__agentcard__buy_connect untrusted-input
  • mcp__agentcard__buy_connect_status untrusted-input
  • mcp__agentcard__manage_subscription untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/sh.agentcard/agentcard/verify?hash=e53814c2c14932303ea24b4bd100c147be04b62649b75d56686ddc809f7209d9" | jq -e '.changed == false'

Pinned hash e53814c2c149, from Nov 19, 2026, 04:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/sh.agentcard/agentcard/changes.xml

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

Badge

Anlyon Radar badge for sh.agentcard/agentcard
[![Anlyon Radar](https://radar.anlyon.com/badge/sh.agentcard/agentcard.svg)](https://radar.anlyon.com/servers/sh.agentcard/agentcard)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

agentcard MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the agentcard MCP server safe?

No scan can promise that. What its definitions show: 55 tools, 37 of which can change, send or delete something, and 6 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the agentcard MCP server delete data?

Yes. 7 tools can delete, cancel or revoke something: buy, close_card, delete_preset, remove_added_card, revoke_connection, link_account and 1 more.

Can the agentcard MCP server do things that cannot be undone?

Yes. 2 tools can send, pay, publish or merge: send_support_message and start_phone_verification.

What tools does the agentcard MCP server have?

55 tools: 7 destructive, 2 irreversible, 28 write, 18 read. buy, close_card, delete_preset, remove_added_card, revoke_connection, link_account, buy_unlink_merchant, send_support_message and 47 more.

Does the agentcard MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the agentcard MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_support_message, submit_user_info and submit_kyc_fields.

Has the agentcard MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 5, 2026. Every change is on this page and in its Atom feed.