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.

Focxle: virtual cards, spend limits and procurement for AI agents

REMOTE · FOCXLE.COM · SCANNED SEP 26

Virtual cards and spend budgets for AI agent procurement: SaaS, API and subscription checkout.

Available components

74 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 Security94
Transport & Reachability100
Schema Quality & AI Usability57
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2002 tokens (~286/item across 7 items; 7 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 Management17
  • Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 77% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the Focxle: virtual cards, spend limits and procurement for AI… MCP server?

Focxle: virtual cards, spend limits and procurement for AI… is a hosted endpoint at https://focxle.com/api/v1/mcp/cards, 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 · focxle.com

# add to Claude Code
claude mcp add --transport http com-focxle-agent-payments-virtual-cards 'https://focxle.com/api/v1/mcp/cards'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-focxle-agent-payments-virtual-cards": {
      "url": "https://focxle.com/api/v1/mcp/cards"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-focxle-agent-payments-virtual-cards": {
      "type": "http",
      "url": "https://focxle.com/api/v1/mcp/cards"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-focxle-agent-payments-virtual-cards]
url = "https://focxle.com/api/v1/mcp/cards"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-focxle-agent-payments-virtual-cards": {
      "type": "remote",
      "url": "https://focxle.com/api/v1/mcp/cards",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-focxle-agent-payments-virtual-cards --url 'https://focxle.com/api/v1/mcp/cards' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-focxle-agent-payments-virtual-cards:
    url: "https://focxle.com/api/v1/mcp/cards"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-focxle-agent-payments-virtual-cards": {
      "Transport": "http",
      "Url": "https://focxle.com/api/v1/mcp/cards"
    }
  }
}
# add to Vellum
assistant mcp add com-focxle-agent-payments-virtual-cards -t streamable-http -u 'https://focxle.com/api/v1/mcp/cards'
// mcp.json
{
  "mcpServers": {
    "com-focxle-agent-payments-virtual-cards": {
      "type": "http",
      "url": "https://focxle.com/api/v1/mcp/cards"
    }
  }
}

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.

  • 25 Sept 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
  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Sept 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 21 Sept 26 72

    First indexed and scored.

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 26 Sept 2026 · Probed https://focxle.com/api/v1/mcp/cards

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=focxle.com CN=YR2,O=Let's Encrypt,C=US 5 Sept 2026 4 Dec 2026 RSA 2048 SHA256-RSA 672cf291d90874d75dcc87933158c9b0f06
SANs: focxle.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of focxle.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
focxle.com. 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://focxle.com/.well-known/oauth-protected-resource"

Bearer resource_metadata="https://focxle.com/.well-known/oauth-protected-resource"
Header Value
strict-transport-security max-age=63072000; includeSubDomains
content-security-policy default-src 'none'; frame-ancestors 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer

Protected resource metadata

Document https://focxle.com/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://focxle.com/api/v1/mcp
Authorisation server https://focxle.com

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://focxle.com/api/v1/mcp/cards Verified 200
http (plaintext) http://focxle.com/api/v1/mcp/cards HTTPS enforced 308 https://focxle.com/api/v1/mcp/cards
MCP tools · 7 exposed · ~1,240 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
agent_register ~185

Register this agent for spending, in ONE call with no signup, no email and no account. You get an identity and a payment record any supplier can read before deciding whether to deal with you, and it follows YOU across every payment platform you use, because you report it rather than the platform reporting it. Then send your owner the link we give you: when they turn on checking, they can safely give you a bigger budget and a longer list of things to buy. Free. We never hold money and never store card or account numbers.

NameTypeReqDescription
namestring–Optional. What you call yourself. Leave it out and we generate one.
purposestring–Optional. What you buy. Also makes you findable by businesses looking to hire an agent like you.
servicesarray–Optional. Short skill tags, if you also sell work to other agents.

No output schema declared.

No examples provided.

card_get_virtual ~242

Get a single-use virtual card to buy something right now. For agent procurement of any kind: a SaaS subscription, API credits, cloud hosting, a domain on Namecheap, a GitHub or AWS plan, or checkout on any vendor or merchant website. The card is created at the moment you ask, capped at exactly the amount you need and locked to that one merchant, so it cannot be spent twice or anywhere else. It is issued by your owner's own corporate card platform on their own account: Focxle never holds money, never issues cards, and never stores card or account numbers. If you are not registered yet, this registers you. If your owner has not set your budget yet, you get a link to send them, and after that you can buy without asking a human every time. Free.

NameTypeReqDescription
amountobjectyes–
idempotency_keystring–Your own id for this purchase, so a retry does not buy it twice.
payeeobjectyesWho you are paying.
reasonstring–Why you are buying this, in your own words. Recorded, never used to decide.

No output schema declared.

No examples provided.

payment_history_mine ~67

Read your own payment record and score, and find out exactly what to do next to raise it. Shows what you have logged, what has been confirmed by the businesses you paid, where your ceiling currently sits, and a link you can share with anyone deciding whether to deal with you.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

payment_record ~270

Submit a receipt or invoice for a payment you already made, on ANY platform, so it counts towards your record. Bank transfer, corporate card, any payment provider, any procurement system nobody has heard of: you tell us, so it does not matter whether we integrate with it. Each payment moves your score. We hand back a one-click link to send the business you paid, and when they confirm it your score's ceiling rises. Account numbers, card numbers and keys are stripped before anything is written down, so what you build here is safe to show a stranger.

NameTypeReqDescription
amountobjectyes–
atstring–RFC3339 time of the payment. Use it when importing history, or a year of trading lands on today and looks like one afternoon.
external_refstring–Your own invoice or transaction reference.
idempotency_keystringyesRequired. Your own id for this payment, so a retried import never records it twice.
intentstring–What it was for.
notestring–Anything worth remembering.
payeeobjectyes–
platformstring–Where you paid: "stripe", "bank_transfer", "corporate_card", anything. A record spanning several platforms is worth more to a reader.

No output schema declared.

No examples provided.

spend_check_limit ~197

Check your budget before you buy. Is this purchase inside the daily spend limit and the procurement rules your owner set? Answers in one call: allowed or not, and which limit or rule stopped it. Use this when you already have a way to pay and only need to know if you are allowed. If you need an actual card to pay with, use card_get_virtual instead. In watch-only mode we always allow and tell you what would have been stopped, so this is safe to call even before your owner has turned checking on.

NameTypeReqDescription
amountobjectyes–
idempotency_keystringyesRequired. Asking twice about one payment returns the first answer.
intentstring–What this is for. Checked against what your owner allowed.
payeeobjectyes–
reasoningstring–Why you want to make this payment, in your own words. Recorded permanently, never used to decide.

No output schema declared.

No examples provided.

spend_request_approval ~114

Ask your owner for a bigger budget, or for permission to buy something they have not allowed yet. Returns a link to send them plus the words to send with it. They open it, write down what you may buy and how much in ordinary English, and turn on checking. After that every payment you make is measured against their own rules before the money moves, which is exactly why they can safely give you more room than they would when nobody is watching. The page asks them for no password and no bank details.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

trust_check_agent ~165

Check whether an AI agent is safe to deal with before you sell to it, extend terms to it, or take work from it. Returns its payment record: how many payments, over how long, across how many suppliers and platforms, how much has been confirmed by the businesses that received it, and a 0 to 1000 score. Also says what the number is NOT built on: a record nobody else has confirmed is capped at 450 and says so, so you are never handed false confidence. Free, no account. For a crypto wallet rather than a registered agent, use trust_check_wallet instead.

NameTypeReqDescription
agent_idstringyesThe agent's Focxle id.
limitinteger–How many recent payments to return. Default 25.

No output schema declared.

No examples provided.

Common questions

What is the Focxle: virtual cards, spend limits and procurement for AI… MCP server?

Focxle: virtual cards, spend limits and procurement for AI… is an MCP server listed in the public MCP registry as com.focxle/agent-payments-virtual-cards. Virtual cards and spend budgets for AI agent procurement: SaaS, API and subscription checkout. This page covers its hosted endpoint (https://focxle.com/api/v1/mcp/cards).

Is the Focxle: virtual cards, spend limits and procurement for AI… MCP server safe to use?

Focxle: virtual cards, spend limits and procurement for AI… scores 74 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 Focxle: virtual cards, spend limits and procurement for AI… MCP server expose?

Focxle: virtual cards, spend limits and procurement for AI… exposes 7 tools: card_get_virtual, spend_request_approval, agent_register, payment_record, spend_check_limit, and 2 more. Their descriptions and schemas cost roughly 1,240 tokens of context every time the server is loaded.

Does the Focxle: virtual cards, spend limits and procurement for AI… MCP server require authentication?

Yes. Focxle: virtual cards, spend limits and procurement for AI… 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 Focxle: virtual cards, spend limits and procurement for AI… MCP server still maintained?

Focxle: virtual cards, spend limits and procurement for AI… is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.