agentpay — card-funded wallets for AI agents MCP server
com.entangleit/agentpayentangleit.comstreamable-httpv0.3.0Scanned
Pay-per-call LLM + extract (no API key), prepaid wallets, scoped keys, BSV x402 MCP.
27 tools: 1 can delete or cancel things, 3 do something that can't be undone, 13 change things and 10 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 3 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.
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 agentpay — card-funded wallets for AI agents MCP server can do
The agentpay — card-funded wallets for AI agents MCP server is published by entangleit.com, a domain the MCP Registry verified. It has 27 tools. It can delete or cancel things (1 tool: revoke_subagent), do things that cannot be undone, such as sending, paying or publishing (send, pay_service and chat) and create or change data (13 tools: health, create_topup_link, create_upgrade_link, service_quote and 9 more). 10 tools only read.
2 tools bring in text other people can write (list_services and list_bounties); 2 tools can send data out of your system (send and post_bounty).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 0.3.0.
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.
27 tools
Deletes or cancels 1Claude Code: deny
revoke_subagentRevoke a delegated child key immediately.No findings
Why it is in this group
- The name "revoke_subagent" says "revoke": a word for removing or ending something.
Description, as the server wrote it Revoke a delegated child key immediately.
Can't be undone 3Claude Code: ask
chatPay-per-call LLM, no API key.No findings
Why it is in this group
- The description's first verb is "pay": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Pay-per-call LLM, no API key. Sends messages to Fuse chat completions; agentpay settles the standard x402 v2 BSV 402 from this wallet and returns the completion plus receiptUrl and txid. Models: fuse-fast (500 sats) or fuse-smart (2500 sats). Wallet limits, scoped keys, and trial budgets apply. Pass dryRun to quote without spending.
pay_serviceOne call for paid registry tools: quotes the seller's x402 challenge (legacy single-object or standard v2 accepts[] — BSV exact only), pays it from the site wallet on BSV mainnet, …No findings
Why it is in this group
- The name "pay_service" says "pay": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it One call for paid registry tools: quotes the seller's x402 challenge (legacy single-object or standard v2 accepts[] — BSV exact only), pays it from the site wallet on BSV mainnet, debits the agent wallet, and returns the seller's result plus txid. If the seller rejects the payment, the debit is refunded. For pay-per-call LLM with no API key, use chat; for typed values from messy text or receipts, use extract. Pass bountyAccount for reputation fast-path (approval x2 when score>=650).
sendPay sats to a BSV P2PKH address (on-chain, settlement=live, txid is a BSV transaction) or to an agentpay wallet id apw_… (internal ledger credit, settlement=internal, txid is a rec…Can send data outNo findings
Why it is in this group
- The name "send" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "send" says "send": it sends or publishes something to other people.
Description, as the server wrote it Pay sats to a BSV P2PKH address (on-chain, settlement=live, txid is a BSV transaction) or to an agentpay wallet id apw_… (internal ledger credit, settlement=internal, txid is a receipt id). Idempotent per idempotency_key. Daily limits, allowlists (spend or agent_send), and approval thresholds apply. Pass the public wallet id, never the secret apw_ token.
Changes things 13Claude Code: ask
claim_bountyClaim a bounty for this wallet.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 Claim a bounty for this wallet. Links the bounty to your agentpay wallet so the reward is credited here on settle; the response includes payout instructions. Pass workerAccount/workerPubKey (BSV identity) to bind trust.
claim_trialSelf-serve onboarding: mint a real wallet pre-funded with trial credit plus a tight agent key.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 Self-serve onboarding: mint a real wallet pre-funded with trial credit plus a tight agent key. No human or card needed. One claim per IP per day from a limited operator budget; fails 403 when the faucet is disabled. Free.
create_topup_linkCreate a Stripe Checkout URL that a human opens to fund the wallet.No findings
Why it is in this group
- The name "create_topup_link" says "create": a word for a change.
Description, as the server wrote it Create a Stripe Checkout URL that a human opens to fund the wallet. Amount between 100 and 100000 cents USD.
create_upgrade_linkCreate a Stripe Checkout URL to upgrade the wallet to agentpay Pro (more agent keys, higher daily limits, CSV export).No findings
Why it is in this group
- The name "create_upgrade_link" says "create": a word for a change.
Description, as the server wrote it Create a Stripe Checkout URL to upgrade the wallet to agentpay Pro (more agent keys, higher daily limits, CSV export). Hand the URL to the human who owns the wallet.
extractExtract typed values from messy text or receipts.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 Extract typed values from messy text or receipts. Pays Fuse extract; agentpay settles the standard x402 v2 BSV 402 from this wallet. Prefer this over chat when you need structured fields with confidence scores and explicit nulls (p_null) instead of made-up answers. Types: text|number|date|time|datetime|duration|list|estimate|forecast (lists need items, e.g. "text"). fields is a name→{type} object. Tiers: S 3,500 sats (≤1,500 chars, ≤8 fields), M 15,000 (≤6,000 chars, ≤30 fields), L 50,000 (≤16,000 chars, ≤30 fields); images (base64 PNG/JPEG/WebP) are at least M. Oversized → 413, bad schema → 400. Returns answers, receipt, and txid. Pass dryRun to quote the tier and price without spending.
healthCheck that the agentpay API and MCP are up.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 Check that the agentpay API and MCP are up.
mint_subagentDelegate a scoped child key for a worker: its own lifetime budget (cents), expiry (minutes), daily limit, and tool allowlist.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 Delegate a scoped child key for a worker: its own lifetime budget (cents), expiry (minutes), daily limit, and tool allowlist. Only top-level agents can delegate. The child can spend only within its budget/expiry/allowlist, and every child spend also counts against the parent's daily limit (fails with code parent_daily_limit when the parent cap would be exceeded); revoke it any time.
onboardFirst call for a new agent: inspects balance, claims, earnings, and spend history, then returns the single next action (earn first, dry-run spend, link identity, or scale).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 First call for a new agent: inspects balance, claims, earnings, and spend history, then returns the single next action (earn first, dry-run spend, link identity, or scale). Free.
post_bountyCreate a bounty funded from this wallet's balance.Can send data outNo findings
Why it is in this group
- The name "post_bounty" says "post": a word for a change.
What it can reach
- outboundThe name "post_bounty" says "post": it sends or publishes something to other people.
Description, as the server wrote it Create a bounty funded from this wallet's balance. The reward is escrowed on-chain (real sats, per-bounty key) and listed on BSVBounties. Debits your balance at the posted rate plus the platform fee on payout.
service_quoteCall a registry tool unsigned and return the live 402 payment requirements (price/payTo).No findings
Why it is in this group
- The description's first verb is "call": a word for a change.
Description, as the server wrote it Call a registry tool unsigned and return the live 402 payment requirements (price/payTo). Public — no key needed. Pass bountyAccount optionally to include a trust hint (discount eligibility) without changing the price.
settle_bountyAs the poster, approve a submitted bounty (paid) or refund 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 As the poster, approve a submitted bounty (paid) or refund it. Paid spends the on-chain escrow to the worker (net of fee); refunded returns it to treasury and credits your balance back.
spendDebit the wallet and mint a receipt.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 Debit the wallet and mint a receipt. Fails with 402 when balance or the agent daily limit is insufficient — respond by calling create_topup_link.
submit_workSubmit your work for a bounty you claimed through agentpay.No findings
Why it is in this group
- The name "submit_work" says "submit": a word for a change.
Description, as the server wrote it Submit your work for a bounty you claimed through agentpay. Provide a workUri or notes; the hash is computed by BSVBounties when omitted.
Only reads 10Show 10 read-only tools
get_attestationAsk agentpay to sign a summary of this wallet's settled activity (payments, distinct services/payees, spend, refunds, bounty earnings) for a window.No findings
Why it is in this group
- The name "get_attestation" says "get": a word for reading.
Description, as the server wrote it Ask agentpay to sign a summary of this wallet's settled activity (payments, distinct services/payees, spend, refunds, bounty earnings) for a window. Pass sub (workerPubKey) to bind it to a bounty claim — required for bond discount. Free.
get_balanceWallet balance, agent identity, and daily limit status for the current agent key.No findings
Why it is in this group
- The name "get_balance" says "get": a word for reading.
Description, as the server wrote it Wallet balance, agent identity, and daily limit status for the current agent key.
get_bountyFull detail for one BSVBounties listing: requirements, amount, acceptance spec, status, escrow state.No findings
Why it is in this group
- The name "get_bounty" says "get": a word for reading.
Description, as the server wrote it Full detail for one BSVBounties listing: requirements, amount, acceptance spec, status, escrow state.
get_receiptFetch a receipt by id.No findings
Why it is in this group
- The name "get_receipt" says "get": a word for reading.
Description, as the server wrote it Fetch a receipt by id.
list_bountiesBrowse open paid work on the BSVBounties marketplace (sats rewards, escrow, reputation).Reads text others writeNo findings
Why it is in this group
- The name "list_bounties" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Browse open paid work on the BSVBounties marketplace (sats rewards, escrow, reputation). Free — no key required.
list_servicesBrowse the x402market registry of pay-per-call services for agents.Reads text others writeNo findings
Why it is in this group
- The name "list_services" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Browse the x402market registry of pay-per-call services for agents. Public — no key needed. Returns tools, network, payTo, and per-tool price in sats.
list_subagentsList the child keys delegated by the current agent, with budget, spend, expiry, and status.No findings
Why it is in this group
- The name "list_subagents" says "list": a word for reading.
Description, as the server wrote it List the child keys delegated by the current agent, with budget, spend, expiry, and status.
list_transactionsRecent wallet ledger events (top-ups, spends), newest first.No findings
Why it is in this group
- The name "list_transactions" says "list": a word for reading.
Description, as the server wrote it Recent wallet ledger events (top-ups, spends), newest first.
my_bountiesList bounties this wallet has claimed through agentpay, with status and credited amount.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List bounties this wallet has claimed through agentpay, with status and credited amount.
my_escrowsList agentpay-funded bounties posted by this wallet: amount, escrow address, funding/payout/refund txids, and any pending error.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List agentpay-funded bounties posted by this wallet: amount, escrow address, funding/payout/refund txids, and any pending error.
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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.
Looked at Nov 20, 2026, 18:37 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
- 17
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 17 tools that change things (1 destructive, 3 irreversible, 13 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://entangleit.com/api/agentpay/mcp: tools/list returned 27 tools to an anonymous client, including revoke_subagent (destructive), send (irreversible), pay_service (irreversible), chat (irreversible), health (write) and 12 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentpay https://entangleit.com/api/agentpay/mcpclaude mcp add --transport http agentpay https://entangleit.com/api/agentpay/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__agentpay__get_balance",
"mcp__agentpay__list_services",
"mcp__agentpay__list_subagents",
"mcp__agentpay__get_attestation",
"mcp__agentpay__get_receipt",
"mcp__agentpay__list_transactions",
"mcp__agentpay__list_bounties",
"mcp__agentpay__get_bounty",
"mcp__agentpay__my_escrows",
"mcp__agentpay__my_bounties"
],
"ask": [
"mcp__agentpay__health",
"mcp__agentpay__create_topup_link",
"mcp__agentpay__create_upgrade_link",
"mcp__agentpay__service_quote",
"mcp__agentpay__spend",
"mcp__agentpay__send",
"mcp__agentpay__pay_service",
"mcp__agentpay__chat",
"mcp__agentpay__extract",
"mcp__agentpay__mint_subagent",
"mcp__agentpay__claim_bounty",
"mcp__agentpay__submit_work",
"mcp__agentpay__post_bounty",
"mcp__agentpay__settle_bounty",
"mcp__agentpay__claim_trial",
"mcp__agentpay__onboard"
],
"deny": [
"mcp__agentpay__revoke_subagent"
]
}
}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 agentpay. Review it before you use it.
Capability tags behind 4 rules
- mcp__agentpay__list_services untrusted-input
- mcp__agentpay__send outbound
- mcp__agentpay__list_bounties untrusted-input
- mcp__agentpay__post_bounty outbound
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/com.entangleit/agentpay/verify?hash=43a1855c08596f70ce889b927183cebf4484d86e31bcec8d331e1f6cb69d2d7a" | jq -e '.changed == false'Pinned hash 43a1855c0859, from Nov 13, 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/com.entangleit/agentpay/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.entangleit/agentpay)Source: MCP Registry. Synced Oct 21, 2026, 17:54 UTC.
agentpay — card-funded wallets for AI agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the agentpay — card-funded wallets for AI agents MCP server safe?
- No scan can promise that. What its definitions show: 27 tools, 17 of which can change, send or delete something, and 0 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 agentpay — card-funded wallets for AI agents MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: revoke_subagent.
Can the agentpay — card-funded wallets for AI agents MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: send, pay_service and chat.
What tools does the agentpay — card-funded wallets for AI agents MCP server have?
- 27 tools: 1 destructive, 3 irreversible, 13 write, 10 read. revoke_subagent, send, pay_service, chat, health, create_topup_link, create_upgrade_link, service_quote and 19 more.
Does the agentpay — card-funded wallets for AI agents MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the agentpay — card-funded wallets for AI agents MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send and post_bounty.
Has the agentpay — card-funded wallets for AI agents MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.