# io.github.joepangallo/agent-pay (npm · mcp-server-agentpay)

Payment gateway for AI agents with tool discovery, provisioning, metering, and reliability tools.

- Trust score: 64/100 (medium)
- Change this week: +24
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `mcp-server-agentpay`: 64/100 (this document), [markdown](https://verifymcp.io/servers/joepangallo-agent-pay/mcp-server-agentpay.md), [page](https://verifymcp.io/servers/joepangallo-agent-pay/mcp-server-agentpay)

## Channel facts

- Registry: `npm`
- Package: `mcp-server-agentpay`
- Version: `1.1.2`
- 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 (95 of 99), 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 (95 of 99), 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 132 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 897 tokens (~69/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 joepangallo-agent-pay -- npx -y mcp-server-agentpay
```

### Codex

```bash
codex mcp add joepangallo-agent-pay -- npx -y mcp-server-agentpay
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "joepangallo-agent-pay": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-server-agentpay"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add joepangallo-agent-pay --command npx --arg -y --arg mcp-server-agentpay
```

### Hermes

```yaml
mcp_servers:
  joepangallo-agent-pay:
    command: "npx"
    args: ["-y", "mcp-server-agentpay"]
```

### Other

```json
{
  "mcpServers": {
    "joepangallo-agent-pay": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-agentpay"
      ]
    }
  }
}
```

## 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 64, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 60, +52)

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

### 2026-08-01 (score 8, +8)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 0, −40)

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

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (13)

### `discover_tools` (~69 tokens)

Search for available AI tools by keyword or capability. Returns matching tools with descriptions, methods, and per-call pricing. Use this to find what tools are available before calling them.

Input parameters:

- `query` (string, required): Search keyword (e.g. 'security', 'seo', 'indexing', 'vulnerability')

### `list_tools` (~30 tokens)

List all available tools in the AgentPay gateway with their descriptions, methods, and pricing. No authentication required.

### `check_balance` (~32 tokens)

Check your AgentPay wallet balance, total credits funded, total spent, and which tools you have provisioned access to.

### `call_tool` (~118 tokens)

Call any tool method through the AgentPay gateway. Automatically provisions access on first use. Credits are deducted per call. Use discover_tools or list_tools first to see available tools and methods.

Input parameters:

- `method` (string, required): Method name (e.g. 'security_scan', 'scan_sitemap')
- `params_json` (string): Method parameters as JSON string (e.g. '{"url": "example.com"}'). Omit if no params needed.
- `tool` (string, required): Tool ID (e.g. 'agent-audit', 'indexforge')

### `provision_tool` (~73 tokens)

Pre-provision access to a specific tool. This auto-creates an account on the tool's backend. Not required - call_tool auto-provisions on first use - but useful to confirm access before making calls.

Input parameters:

- `tool` (string, required): Tool ID to provision (e.g. 'indexforge', 'agent-audit')

### `get_usage` (~54 tokens)

View your recent tool call history - which tools you called, what methods, how much each cost, and when.

Input parameters:

- `limit` (integer): Number of recent calls to show (default: 20, max: 200)

### `fund_wallet_stripe` (~88 tokens)

Get a Stripe checkout URL to add credits. Requires a human to open the link and pay. Use fund_wallet_x402 for fully autonomous crypto payments instead.

Input parameters:

- `package` (string, required): Credit package: test ($1/1cr), starter ($25/25cr), pro ($100/103cr, 3% bonus), scale ($500/525cr, 5% bonus)

### `fund_wallet_x402` (~115 tokens)

Get x402 crypto funding info for your wallet. Returns the endpoint URL, network, and setup instructions. To actually pay, your HTTP client needs @x402/fetch which automatically handles the 402 payment flow with USDC. This is the fully autonomous funding method - no human needed.

Input parameters:

- `package` (string, required): Credit package: test ($1/1cr), starter ($25/25cr), pro ($100/103cr, 3% bonus), scale ($500/525cr, 5% bonus)

### `x402_info` (~33 tokens)

Get information about x402 crypto payment support - which networks, tokens, and funding options are available for autonomous wallet funding.

### `reliability_dashboard` (~46 tokens)

View the full reliability dashboard - circuit breaker states, health metrics (latency p50/p95/p99, success rates), and recent events for all tool backends. Requires admin key.

### `reliability_tool_detail` (~59 tokens)

Get detailed reliability info for a specific tool - circuit breaker state, config (thresholds, timeouts), health metrics, and recent events.

Input parameters:

- `tool_id` (string, required): Tool ID (e.g. 'agent-audit', 'indexforge')

### `reliability_reset` (~64 tokens)

Force-close a tripped circuit breaker for a tool, allowing calls to resume immediately. Use when a backend has recovered but the circuit has not automatically reset yet.

Input parameters:

- `tool_id` (string, required): Tool ID to reset (e.g. 'agent-audit', 'indexforge')

### `reliability_config` (~116 tokens)

Update reliability settings for a specific tool - failure threshold, recovery timeout, and request timeout. Changes take effect immediately.

Input parameters:

- `failure_threshold` (integer): Number of consecutive failures before circuit opens (1-100)
- `recovery_timeout_ms` (integer): Milliseconds before OPEN circuit tries recovery (5000-600000)
- `request_timeout_ms` (integer): Per-request timeout in milliseconds (1000-600000)
- `tool_id` (string, required): Tool ID to configure (e.g. 'agent-audit', 'indexforge')

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/joepangallo-agent-pay/mcp-server-agentpay#diagnostics

## Score history

- 2026-08-03: 64
- 2026-08-02: 60
- 2026-08-01: 8
- 2026-07-31: 0
- 2026-07-30: 40
- 2026-07-28: 40
- 2026-07-27: 40

## Links

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