# io.github.npraught/orcpin (npm · orcpin-mcp)

Paid x402 facts for AI agents: on-chain snapshots, endpoint reliability, trade math, free directory

- Trust score: 61/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `orcpin-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/npraught-orcpin/orcpin-mcp.md), [page](https://verifymcp.io/servers/npraught-orcpin/orcpin-mcp)

## Channel facts

- Registry: `npm`
- Package: `orcpin-mcp`
- Version: `0.3.0`
- 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 (113 of 117), 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 (113 of 117), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1055 tokens (~117/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 56% 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 npraught-orcpin -- npx -y orcpin-mcp
```

### Codex

```bash
codex mcp add npraught-orcpin -- npx -y orcpin-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add npraught-orcpin --command npx --arg -y --arg orcpin-mcp
```

### Hermes

```yaml
mcp_servers:
  npraught-orcpin:
    command: "npx"
    args: ["-y", "orcpin-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "npraught-orcpin": {
      "command": "npx",
      "args": [
        "-y",
        "orcpin-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 61, +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 60, +46)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-07-31 (score 14, −6)

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

### 2026-07-30 (score 20, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 38)

First indexed and scored.

## MCP tools (9)

### `orcpin_x402_directory` (~208 tokens)

FREE — no wallet or payment needed. Search the public x402 ecosystem: a demand-ordered directory of ~1000 paid endpoints listed on the CDP Bazaar, ranked by distinct paying wallets in the last 30 days. Filter by text, network, and maximum price. Use this to DISCOVER endpoints an agent could pay; each result says whether Orcpin holds reliability measurements for it (the measurements themselves are orcpin_endpoint_reliability).

Input parameters:

- `limit` (integer): Page size, default 50.
- `max_price` (string): Maximum advertised price in USD, e.g. "0.01". Endpoints with no advertised price are excluded.
- `network` (string): Exact network id as listed upstream, e.g. base, eip155:8453, solana. Matched exactly, not as a substring.
- `offset` (integer): Pagination offset.
- `q` (string): Text match over resource URL, service name and description.

### `orcpin_wallet_snapshot` (~64 tokens)

Block-anchored wallet snapshot on Base: native ETH + tracked ERC-20 balances, account flags, and derived metrics (wallet type, activity tier, gas runway). Paid via x402 (~$0.02 USDC).

Input parameters:

- `address` (string, required)

### `orcpin_defi_snapshot` (~81 tokens)

DeFi position + risk snapshot on Base: wallet balances plus live Aave v3 collateral, debt, borrowing power, health factor, and derived risk metrics (net equity, LTV utilization, leverage, health-factor band, collateral drawdown tolerance). Paid via x402 (~$0.05 USDC).

Input parameters:

- `address` (string, required)

### `orcpin_batch_snapshot` (~77 tokens)

Batch wallet snapshots for multiple Base addresses in one paid call, all anchored to a single block. Efficient multi-wallet / treasury monitoring. Volume-tiered via x402: ~$0.02/address, 20–40% off at 10/50/100 (up to 1000).

Input parameters:

- `addresses` (array, required)

### `orcpin_endpoint_reliability` (~96 tokens)

Pre-flight an x402 endpoint BEFORE paying it. Returns factual service-delivery measurements (reachability/uptime rate, valid-402 rate, latency p50/p95/p99, last status, sampled paid delivery verification). Facts only — no trust score, no 'scam' label; apply your own thresholds. Paid via x402 (~$0.01 USDC).

Input parameters:

- `url` (string, required)

### `orcpin_endpoint_reliability_batch` (~99 tokens)

Sweep an agent's whole tool list of x402 endpoints in one paid call: factual delivery measurements (uptime, valid-402 rate, latency, last status) for each. Facts only — not an endorsement or rating. Volume-tiered via x402: ~$0.01/endpoint, 20–40% off at 10/50/100 (up to 150).

Input parameters:

- `urls` (array, required)

### `orcpin_holding_period` (~155 tokens)

Trade-lot holding-period + realized-gain calculator for trading agents. Send your tax lots (and optionally a proposed sell): returns per-lot days held, the exact date each lot's gain character turns long-term, and FIFO / specific-identification sell allocation with realized gain per lot and per-character totals. Deterministic arithmetic with the published threshold cited (IRC §1222) — counts, dates, and dollars only, never advice. Nothing is stored server-side. Paid via x402 (~$0.02 USDC).

Input parameters:

- `asOf` (string, required): Evaluation date (YYYY-MM-DD)
- `lots` (array, required)
- `sell` (object): Optional proposed sell to allocate across the lots

### `orcpin_day_trade_count` (~161 tokens)

Count same-day round trips in the rolling five-TRADING-day window (versioned NYSE holiday calendar — the math agents hand-roll wrong). Send your trades: returns matched same-day buy/sell pairs per symbol, total in-window trades, and the ratio, with FINRA Rule 4210's pattern-day-trader definition cited separately as a published fact. Counts only — the comparison is yours. Nothing is stored. Paid via x402 (~$0.02 USDC).

Input parameters:

- `asOf` (string, required): Evaluation date (YYYY-MM-DD); anchors the 5-trading-day window
- `trades` (array, required)
- `tradesCoverageFrom`: Earliest date your supplied trades cover; short coverage is flagged, never hidden

### `orcpin_settlement_dates` (~114 tokens)

T+1 settlement dates for your equity trades on the versioned NYSE holiday calendar: settlement date per trade and whether it has settled as of a given date, with SEC Rule 15c6-1 cited separately as a published rule. Dates and counts only — never a violation determination. Nothing is stored. Paid via x402 (~$0.02 USDC).

Input parameters:

- `asOf` (string, required): Date to evaluate settled/unsettled against (YYYY-MM-DD)
- `trades` (array, required)

## Diagnostics

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

## Score history

- 2026-08-03: 61
- 2026-08-02: 60
- 2026-08-01: 14
- 2026-07-31: 14
- 2026-07-30: 20
- 2026-07-28: 38
- 2026-07-27: 38

## Links

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