# io.github.stevemilton/buyforme-mcp (npm · buyforme-mcp)

BuyForMe: pay any x402 URL (USD or EUR) with ArisPay delegated custody. Alias of payagent-mcp.

- Trust score: 62/100 (medium)
- Change this week: −8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `buyforme-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/stevemilton-buyforme-mcp/buyforme-mcp.md), [page](https://verifymcp.io/servers/stevemilton-buyforme-mcp/buyforme-mcp)

## Channel facts

- Registry: `npm`
- Package: `buyforme-mcp`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (106 of 113), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (106 of 113), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1439 tokens (~75/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 70% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add stevemilton-buyforme-mcp -- npx -y buyforme-mcp
```

### Codex

```bash
codex mcp add stevemilton-buyforme-mcp -- npx -y buyforme-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "stevemilton-buyforme-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "buyforme-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add stevemilton-buyforme-mcp --command npx --arg -y --arg buyforme-mcp
```

### Hermes

```yaml
mcp_servers:
  stevemilton-buyforme-mcp:
    command: "npx"
    args: ["-y", "buyforme-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "stevemilton-buyforme-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "buyforme-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 61, +61)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Schema quality: 1181 → 1439
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 0, −31)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 31, −39)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] License: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional] Licence: MIT

### 2026-07-27 (score 70, +50)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 67
- [functional] Licence: MIT

### 2026-07-26 (score 20)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (19)

### `create_user` (~75 tokens)

Cold-start in one call: create an ArisPay user account plus the master funding account. Safe to re-run — it recovers the existing account instead of creating duplicates.

Input parameters:

- `email` (string, required): Email for the new ArisPay account.
- `name` (string): Human name. Falls back to the email local-part.

### `create_wallet` (~120 tokens)

Create a sub-wallet / spending profile. Sub-wallets draw from the master funding account and enforce per-transaction, daily, and monthly spend limits.

Input parameters:

- `allowedDomains` (array): If provided, restrict this sub-wallet to paying only these domains.
- `daily` (integer, required): Daily spend cap in cents.
- `monthly` (integer, required): Monthly spend cap in cents.
- `name` (string, required): Human name for this sub-wallet, e.g. 'Daily' or 'Travel'.
- `perTx` (integer, required): Per-transaction spend cap in cents.

### `list_wallets` (~18 tokens)

List all sub-wallets under this account.

### `fund_wallet` (~116 tokens)

Add money to the master funding account so a sub-wallet can spend. rail='europ' opens the Schuman KYC / vIBAN flow in a browser; rail='card' mints a hosted card-setup URL.

Input parameters:

- `amount` (number): Optional preset amount in dollars.
- `rail` (string, required): Funding rail: 'europ' for SEPA/EURØP, 'card' for debit/credit card.
- `wallet` (string, required): Name of a sub-wallet (used only for handoff context).

### `get_balance` (~56 tokens)

Show the master funding-account balance(s) and a sub-wallet's spend limits. If no wallet is named, lists all sub-wallets.

Input parameters:

- `wallet` (string): Optional sub-wallet name. Omit to list all sub-wallets.

### `pay_merchant` (~166 tokens)

Pay a merchant from the master wallet through a sub-wallet. For balance-rail payments (from FundingAccount), merchantId is required. For card-rail payments, the user must have a verified card on file.

Input parameters:

- `amount` (integer, required): Amount in cents.
- `currency` (string): Currency code. Default: USD.
- `memo` (string, required): Human-readable memo, e.g. 'T-shirt from getwatta.com'.
- `merchantId` (string): Required for balance-rail payments to a registered merchant.
- `merchantUrl` (string, required): Canonical merchant URL for this payment.
- `rail` (string): Force balance or card rail. Default: server picks based on available funding.
- `wallet` (string, required): Name of the sub-wallet to spend through.

### `pay_api` (~98 tokens)

Advanced: make an HTTP request to an x402-protected API, paying with USDC on Base via delegated signing. This is a separate rail from the wallet-centric balance/card flows.

Input parameters:

- `agent` (string): Optional name of a stored x402 payer agent.
- `body` (string)
- `headers` (object)
- `method` (string)
- `url` (string, required): The full URL of the API endpoint to call.

### `create_agent` (~117 tokens)

Advanced: provision an x402 payer agent with its own Base USDC wallet. Use create_wallet instead unless you specifically need to pay x402-protected HTTP resources.

Input parameters:

- `agentType` (string)
- `allowedDomains` (array)
- `daily` (integer, required): Daily spend cap in cents.
- `monthly` (integer, required): Monthly spend cap in cents.
- `name` (string, required): Local identifier for this x402 agent.
- `network` (string)
- `perTx` (integer, required): Per-transaction spend cap in cents.

### `fund_agent` (~39 tokens)

Advanced: get the USDC deposit address for an x402 payer agent.

Input parameters:

- `name` (string, required): Name of a locally-stored x402 agent.

### `get_balance_agent` (~39 tokens)

Advanced: on-chain USDC balance for an x402 payer agent.

Input parameters:

- `name` (string, required): Name of a locally-stored x402 agent.

### `list_agents` (~36 tokens)

Advanced: list x402 payer agents with on-chain wallets.

Input parameters:

- `withBalance` (boolean): Fetch on-chain USDC balance per agent.

### `rename_agent` (~42 tokens)

Advanced: rename an x402 payer agent.

Input parameters:

- `name` (string, required): Current local name of the x402 agent.
- `newName` (string, required): New name.

### `discover_paid_api` (~176 tokens)

Search the ArisPay marketplace for paid APIs by capability or plain-language intent, optionally budget-bounded (integer cents). Read-only — costs nothing and needs no API key. Returns ranked candidates with endpoint URL, price in cents, health and verification flags. Follow up with pay_api to actually call one, or inspect_paid_api to see a URL's exact payment requirements first.

Input parameters:

- `budgetCentsMax` (integer): Maximum acceptable price in INTEGER CENTS (500 = $5.00). Free listings always pass.
- `category` (string): Optional category filter (inference, data, media, search, social, infrastructure, trading, other).
- `limit` (integer): Max results (default 5, max 20).
- `query` (string, required): Capability or plain-language intent, e.g. 'flight search'.

### `inspect_paid_api` (~82 tokens)

Fetch an x402-protected URL WITHOUT paying to see its price, asset, network, and payment requirements. Read-only, never pays — no payment header, no auth, no API key. Use before pay_api to know what a resource costs.

Input parameters:

- `url` (string, required): The URL to inspect. Expected to return HTTP 402 with an x402 challenge.

### `create_enduser` (~52 tokens)

Platform mode: register an end-customer under your account.

Input parameters:

- `email` (string)
- `externalId` (string, required): Your own stable id for this customer.
- `findOrCreate` (boolean)

### `attach_card_for_user` (~58 tokens)

Platform mode: mint a hosted card-entry URL for an end-user.

Input parameters:

- `agentName` (string): Optional x402 agent name to scope the session to.
- `userId` (string, required): ArisPay-internal end-user id.

### `set_user_limits` (~78 tokens)

Platform mode: set per-(user, agent) spend caps.

Input parameters:

- `agentName` (string, required)
- `allowedMcc` (array)
- `blockedMcc` (array)
- `daily` (integer)
- `monthly` (integer)
- `perTx` (integer)
- `userId` (string, required)

### `get_user_status` (~30 tokens)

Platform mode: report an end-user's card and wallet readiness.

Input parameters:

- `userId` (string, required)

### `check_wallet` (~41 tokens)

Legacy diagnostic for x402 payer agents. Use get_balance for wallet-centric balances.

Input parameters:

- `agent` (string): Optional name of a locally-stored x402 agent.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/stevemilton-buyforme-mcp/buyforme-mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 61
- 2026-08-01: 0
- 2026-07-31: 0
- 2026-07-30: 31
- 2026-07-28: 70
- 2026-07-27: 70
- 2026-07-26: 20

## Links

- npm package: https://www.npmjs.com/package/buyforme-mcp
- Socket report: https://socket.dev/npm/package/buyforme-mcp
- Changelog RSS feed: https://verifymcp.io/servers/stevemilton-buyforme-mcp/buyforme-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/stevemilton-buyforme-mcp/buyforme-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/stevemilton-buyforme-mcp/buyforme-mcp