# AgentPay (pypi · mcp-server-agentpay)

x402 micropayments MCP: Xiaohongshu notes and paid APIs settled in USDC on Base.

- Trust score: 78/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `agentpay-xhs-production.up.railway.app`: 79/100, [markdown](https://verifymcp.io/servers/yyxqqq777-agentpay/agentpay-xhs-production.md), [page](https://verifymcp.io/servers/yyxqqq777-agentpay/agentpay-xhs-production)
- pypi · `mcp-server-agentpay`: 78/100 (this document), [markdown](https://verifymcp.io/servers/yyxqqq777-agentpay/mcp-server-agentpay.md), [page](https://verifymcp.io/servers/yyxqqq777-agentpay/mcp-server-agentpay)

## Channel facts

- Registry: `pypi`
- Package: `mcp-server-agentpay`
- Version: `0.1.3`
- 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 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 52 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 13 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 607 tokens (~121/item across 5 items; 4 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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 MCP server?

AgentPay runs locally as a PyPI package, launched with uvx mcp-server-agentpay. 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 yyxqqq777-agentpay -- uvx mcp-server-agentpay
```

### Cursor

```json
{
  "mcpServers": {
    "yyxqqq777-agentpay": {
      "command": "uvx",
      "args": [
        "mcp-server-agentpay"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "yyxqqq777-agentpay": {
      "command": "uvx",
      "args": [
        "mcp-server-agentpay"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add yyxqqq777-agentpay -- uvx mcp-server-agentpay
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "yyxqqq777-agentpay": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-server-agentpay"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add yyxqqq777-agentpay --command uvx --arg mcp-server-agentpay
```

### Hermes

```yaml
mcp_servers:
  yyxqqq777-agentpay:
    command: "uvx"
    args: ["mcp-server-agentpay"]
```

### Netclaw

```json
{
  "McpServers": {
    "yyxqqq777-agentpay": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-server-agentpay"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add yyxqqq777-agentpay -t stdio -c uvx -a mcp-server-agentpay
```

### Other

```json
{
  "mcpServers": {
    "yyxqqq777-agentpay": {
      "command": "uvx",
      "args": [
        "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.

### 2026-09-20 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-19 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 62, −14)

- [security regression] Malware scan: pass → unverified

### 2026-09-15 (score 76, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 60, −12)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.23

### 2026-09-12 (score 72, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-11 (score 57, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-08 (score 72, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (4)

### `xhs_get_note_detail` (~160 tokens)

Get Xiaohongshu note detail

Fetch one Xiaohongshu (小红书) note by share URL or 24-char note_id and return title, description, author, engagement stats, images, and video URL as JSON. Call this when the user pastes an xiaohongshu.com/explore link or a note id. Settles ~0.01 USDC via x402 on each successful call.

Input parameters:

- `note` (string, required): Xiaohongshu note share URL or 24-character hex note_id. Example: https://www.xiaohongshu.com/explore/6a95a1f30000000026019ab7
- `note_type`: Optional media hint to speed lookup: image, video, 图文, or 视频.

Output parameters:

- `result` (string)

### `xhs_get_user_notes` (~106 tokens)

List Xiaohongshu user notes

List posted notes for a Xiaohongshu user_id (paginated). Returns note summaries and next_cursor for pagination. Use when the user asks for a creator's recent posts. Settles ~0.01 USDC via x402 per page.

Input parameters:

- `cursor`: Pagination cursor from the previous response's next_cursor. Omit or null for the first page.
- `user_id` (string, required): Xiaohongshu user ID string from a profile or prior note author.

Output parameters:

- `result` (string)

### `china_wholesale_pricing_query` (~130 tokens)

Query China wholesale pricing

Search factory-direct wholesale pricing samples for a product keyword (1688 / Yiwu style catalog). Returns items with MOQ, unit price USD, factory location, and supplier verification flags. Use for China sourcing research. Settles ~0.01 USDC via x402 per query.

Input parameters:

- `category_id`: Optional category filter ID when the user specifies a catalog category.
- `keyword` (string, required): Product search query in English or Chinese, e.g. 'wireless earbuds' or '蓝牙耳机'.
- `max_price`: Optional maximum target unit price in USD to filter results.

Output parameters:

- `result` (string)

### `agentpay_payment_status` (~78 tokens)

Check AgentPay payment status

Return AgentPay payment configuration without charging: network, price, spending limit, payment mode, gateway URL, and agent wallet address. Call this before paid tools to verify the wallet is configured, or after a payment error.

Input parameters:

- `include_wallet` (boolean): If true (default), include the derived agent wallet address from AGENT_PRIVATE_KEY.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/yyxqqq777-agentpay/mcp-server-agentpay#diagnostics

## Score history

- 2026-09-20: 78
- 2026-09-19: 63
- 2026-09-18: 62
- 2026-09-17: 62
- 2026-09-16: 76
- 2026-09-15: 76
- 2026-09-14: 60
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 57
- 2026-09-10: 72
- 2026-09-09: 72
- 2026-09-08: 72
- 2026-09-07: 57

## Common questions

### What is the AgentPay MCP server?

AgentPay is an MCP server listed in the public MCP registry as io.github.yyxqqq777/agentpay. x402 micropayments MCP: Xiaohongshu notes and paid APIs settled in USDC on Base. This page covers its PyPI package (mcp-server-agentpay).

### Is the AgentPay MCP server safe to use?

AgentPay scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 MCP server expose?

AgentPay exposes 4 tools: xhs_get_note_detail, xhs_get_user_notes, china_wholesale_pricing_query, agentpay_payment_status. Their descriptions and schemas cost roughly 474 tokens of context every time the server is loaded.

### Is the AgentPay MCP server still maintained?

AgentPay 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.

### What licence is the AgentPay MCP server under?

AgentPay declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/mcp-server-agentpay/
- Socket report: https://socket.dev/pypi/package/mcp-server-agentpay
- Repository: https://github.com/yyxqqq777/mcp-server-agentpay
- Changelog RSS feed: https://verifymcp.io/servers/yyxqqq777-agentpay/mcp-server-agentpay.xml
- Changelog JSON feed: https://verifymcp.io/servers/yyxqqq777-agentpay/mcp-server-agentpay.json
- HTML version of this page: https://verifymcp.io/servers/yyxqqq777-agentpay/mcp-server-agentpay