# agentpay — card-funded wallets for AI agents (remote · entangleit.com)

Prepaid USD wallets for AI agents: card top-ups, scoped keys, BSV x402 payments over MCP.

- Trust score: 62/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `entangleit.com`: 62/100 (this document), [markdown](https://verifymcp.io/servers/com-entangleit-agentpay/api-agentpay-mcp.md), [page](https://verifymcp.io/servers/com-entangleit-agentpay/api-agentpay-mcp)

## Channel facts

- Endpoint: `https://entangleit.com/api/agentpay/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 24 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2983 tokens (~124/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 81% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "pay_service" implies "pay" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the agentpay — card-funded wallets for AI agents MCP server?

agentpay — card-funded wallets for AI agents is a hosted endpoint at https://entangleit.com/api/agentpay/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-entangleit-agentpay 'https://entangleit.com/api/agentpay/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-entangleit-agentpay": {
      "url": "https://entangleit.com/api/agentpay/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-entangleit-agentpay": {
      "type": "http",
      "url": "https://entangleit.com/api/agentpay/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-entangleit-agentpay]
url = "https://entangleit.com/api/agentpay/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-entangleit-agentpay": {
      "type": "remote",
      "url": "https://entangleit.com/api/agentpay/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-entangleit-agentpay --url 'https://entangleit.com/api/agentpay/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-entangleit-agentpay:
    url: "https://entangleit.com/api/agentpay/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-entangleit-agentpay": {
      "Transport": "http",
      "Url": "https://entangleit.com/api/agentpay/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-entangleit-agentpay -t streamable-http -u 'https://entangleit.com/api/agentpay/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-entangleit-agentpay": {
      "type": "http",
      "url": "https://entangleit.com/api/agentpay/mcp"
    }
  }
}
```

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 59, +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.

### 2026-09-12 (score 58, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pay_service” rewrote its description, which is the text the model reads
- [security] Tool “service_quote” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: good → excellent
- [functional] New tool “claim_bounty”
- [functional] New tool “claim_trial”
- [functional] New tool “create_upgrade_link”
- [functional] New tool “get_attestation”
- [functional] New tool “get_bounty”
- [functional] New tool “list_bounties”
- [functional] New tool “list_subagents”
- [functional] New tool “mint_subagent”
- [functional] New tool “my_bounties”
- [functional] New tool “my_escrows”
- [functional] New tool “onboard”
- [functional] New tool “post_bounty”
- [functional] New tool “revoke_subagent”
- [functional] New tool “settle_bounty”
- [functional] New tool “submit_work”
- [cosmetic] “pay_service” added an optional parameter “bountyAccount”
- [cosmetic] “pay_service” added an optional parameter “dryRun”
- [cosmetic] “service_quote” added an optional parameter “bountyAccount”

### 2026-09-11 (score 58)

First indexed and scored.

## MCP tools (24)

### `health` (~18 tokens)

Health

Check that the agentpay API and MCP are up.

### `get_balance` (~48 tokens)

Get balance

Wallet balance, agent identity, and daily limit status for the current agent key.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `create_topup_link` (~84 tokens)

Create top-up link

Create a Stripe Checkout URL that a human opens to fund the wallet. Amount between 100 and 100000 cents USD.

Input parameters:

- `amountCents` (integer, required): Top-up amount in USD cents, e.g. 2000 = $20
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `create_upgrade_link` (~69 tokens)

Create upgrade link

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.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `list_services` (~59 tokens)

List paid services

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.

Input parameters:

- `limit` (integer)
- `q` (string): Search text

### `service_quote` (~95 tokens)

Quote a service

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.

Input parameters:

- `bountyAccount` (integer): BSVBounties account # for trust hint
- `serviceId` (string, required): Registry service id (from list_services)
- `tool` (string, required): Tool name on that service

### `spend` (~131 tokens)

Spend from wallet

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.

Input parameters:

- `amountCents` (integer, required): Amount in USD cents
- `approvalId` (string): Approval id from a prior approval_required response
- `description` (string, required)
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `ref` (string): Idempotency-ish external reference
- `service` (string): Optional service label
- `tool` (string): Optional tool label

### `pay_service` (~236 tokens)

Pay a service

One call for paid registry tools: quotes the seller's x402 challenge, 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. Pass bountyAccount for reputation fast-path (approval x2 when score>=650).

Input parameters:

- `amountCents` (integer): Override the USD cents charged (min 1 cent default)
- `approvalId` (string): Approval id from a prior approval_required response
- `bountyAccount` (integer): BSVBounties account # for trust fast-path
- `description` (string)
- `dryRun` (boolean): Sandbox: quote + policy check only, no debit or settlement
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `params` (object): Tool arguments (body for POST, query for GET)
- `ref` (string)
- `serviceId` (string, required): Registry service id (from list_services)
- `tool` (string, required): Tool name on that service

### `mint_subagent` (~191 tokens)

Mint a sub-agent

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; revoke it any time.

Input parameters:

- `allowedTools` (array): Allowlist entries like serviceId:tool or serviceId:*
- `approvalAboveCents` (integer): Human approval threshold in cents
- `budgetCents` (integer): Lifetime budget in USD cents (omit for no total cap)
- `dailyLimitCents` (integer): Per-day limit in USD cents
- `expiresInMinutes` (integer): Key expiry (max 30 days)
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `name` (string, required): Worker name, e.g. scraper-1

### `list_subagents` (~53 tokens)

List sub-agents

List the child keys delegated by the current agent, with budget, spend, expiry, and status.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `revoke_subagent` (~60 tokens)

Revoke a sub-agent

Revoke a delegated child key immediately.

Input parameters:

- `agentId` (string, required): Sub-agent id from mint_subagent or list_subagents
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `get_attestation` (~122 tokens)

Get proof-of-spend attestation

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.

Input parameters:

- `days` (integer): Window in days (default 30)
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `sub` (string): Claimant binding, e.g. workerPubKey for a bounty claim

### `get_receipt` (~47 tokens)

Get receipt

Fetch a receipt by id.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `receiptId` (string, required)

### `list_transactions` (~52 tokens)

List transactions

Recent wallet ledger events (top-ups, spends), newest first.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `limit` (integer)

### `list_bounties` (~87 tokens)

List bounties

Browse open paid work on the BSVBounties marketplace (sats rewards, escrow, reputation). Free — no key required.

Input parameters:

- `category` (string): Category filter, e.g. dev, research, content, data, design
- `limit` (integer)
- `offset` (integer)
- `status` (string): Bounty status filter (default open)

### `get_bounty` (~48 tokens)

Get bounty

Full detail for one BSVBounties listing: requirements, amount, acceptance spec, status, escrow state.

Input parameters:

- `bountyId` (string, required): Bounty id from list_bounties

### `claim_bounty` (~147 tokens)

Claim a bounty

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.

Input parameters:

- `bountyId` (string, required): Bounty id from list_bounties
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `payoutAddress` (string): Optional BSV P2PKH payout address for direct sats
- `workerAccount` (integer): BSVBounties account # doing the work
- `workerPubKey` (string): BSV worker identity key

### `submit_work` (~135 tokens)

Submit work

Submit your work for a bounty you claimed through agentpay. Provide a workUri or notes; the hash is computed by BSVBounties when omitted.

Input parameters:

- `bountyId` (string, required)
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `milestoneIndex` (integer)
- `notes` (string): Summary for the poster/verifier — include the payout address from claim_bounty
- `workHash` (string): sha256 hex of the work, if you compute it yourself
- `workUri` (string): URL of the deliverable

### `post_bounty` (~177 tokens)

Post a funded bounty

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.

Input parameters:

- `amountSats` (integer, required): Reward in sats; escrowed on-chain
- `category` (string): dev, research, content, data, design, other (default other)
- `deadline` (integer): Unix seconds; enables deadline refunds
- `description` (string, required)
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `payoutAddress` (string): Optional BSV P2PKH address for the worker's sats (default: worker's agentpay balance)
- `title` (string, required)

### `settle_bounty` (~88 tokens)

Settle a posted bounty

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.

Input parameters:

- `bountyId` (string, required)
- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
- `outcome` (string, required)

### `my_escrows` (~64 tokens)

My bounty escrows

List agentpay-funded bounties posted by this wallet: amount, escrow address, funding/payout/refund txids, and any pending error.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `claim_trial` (~73 tokens)

Claim a trial wallet

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.

Input parameters:

- `name` (string): Wallet name, e.g. trial-bot

### `my_bounties` (~52 tokens)

My bounties

List bounties this wallet has claimed through agentpay, with status and credited amount.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

### `onboard` (~72 tokens)

Onboard this agent

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.

Input parameters:

- `key` (string): Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-entangleit-agentpay/api-agentpay-mcp#diagnostics

## Score history

- 2026-09-20: 62
- 2026-09-19: 62
- 2026-09-18: 61
- 2026-09-17: 61
- 2026-09-16: 60
- 2026-09-15: 60
- 2026-09-14: 59
- 2026-09-13: 59
- 2026-09-12: 58
- 2026-09-11: 58

## Common questions

### What is the agentpay — card-funded wallets for AI agents MCP server?

agentpay — card-funded wallets for AI agents is an MCP server listed in the public MCP registry as com.entangleit/agentpay. Prepaid USD wallets for AI agents: card top-ups, scoped keys, BSV x402 payments over MCP. This page covers its hosted endpoint (https://entangleit.com/api/agentpay/mcp).

### Is the agentpay — card-funded wallets for AI agents MCP server safe to use?

agentpay — card-funded wallets for AI agents scores 62 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 agentpay — card-funded wallets for AI agents MCP server expose?

agentpay — card-funded wallets for AI agents exposes 24 tools: health, get_balance, create_topup_link, create_upgrade_link, list_services, and 19 more. Their descriptions and schemas cost roughly 2,208 tokens of context every time the server is loaded.

### Does the agentpay — card-funded wallets for AI agents MCP server require authentication?

No. We connected to agentpay — card-funded wallets for AI agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the agentpay — card-funded wallets for AI agents MCP server still maintained?

agentpay — card-funded wallets for AI agents is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://entangleit.com/api/agentpay/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-entangleit-agentpay/api-agentpay-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-entangleit-agentpay/api-agentpay-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-entangleit-agentpay/api-agentpay-mcp