# io.github.Antmanbuilds/ari-mcp (npm · ari-mcp)

Fair-price checks, leaderboards, and Ed25519 receipt verification for x402/MPP services.

- Trust score: 74/100 (medium)
- Change this week: +32
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `ari-mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/antmanbuilds-ari-mcp/ari-mcp.md), [page](https://verifymcp.io/servers/antmanbuilds-ari-mcp/ari-mcp)

## Channel facts

- Registry: `npm`
- Package: `ari-mcp`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), 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 (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Antmanbuilds/ARI).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 69 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 996 tokens (~90/item across 11 items; 11 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**: 68/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 3% 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 antmanbuilds-ari-mcp -- npx -y ari-mcp
```

### Codex

```bash
codex mcp add antmanbuilds-ari-mcp -- npx -y ari-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add antmanbuilds-ari-mcp --command npx --arg -y --arg ari-mcp
```

### Hermes

```yaml
mcp_servers:
  antmanbuilds-ari-mcp:
    command: "npx"
    args: ["-y", "ari-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "antmanbuilds-ari-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ari-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.

### 2026-08-02 (score 74, +56)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] The attested source repository moved: Antmanbuilds/ARI
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] First check of Schema quality: unverified
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 18, −27)

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

### 2026-07-31 (score 45, +3)

- [security regression] Malware scan: pass → unverified
- [security improvement] Provenance: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security] The attested source repository moved: Antmanbuilds/ARI
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional] Licence: Apache-2.0

### 2026-07-27 (score 42)

First indexed and scored.

## MCP tools (11)

### `is_fair_price` (~86 tokens)

Check if a quoted price is fair

Compare a quoted price for a known service against ARI's current fair-market value (FMV) band. Returns a verdict (green/amber/red), the FMV, the band, the percentile, the sample size, and a citable signed receipt id.

Input parameters:

- `amount_usd` (number, required)
- `slug` (string, required)
- `unit` (string)

### `get_fmv` (~51 tokens)

Get the fair-market value for a service

Look up the current FMV (median + low/high band) for an indexed service. Use this when you need the price you'd quote a counterparty before knowing their ask.

Input parameters:

- `slug` (string, required)

### `list_services` (~93 tokens)

List indexed services

Browse the ARI service index. Filter by protocol (`x402`, `mpp`), category, or free-text search. Returns paginated rows with slug, name, vendor, protocol, category, FMV, and last-observed-at.

Input parameters:

- `category` (string)
- `limit` (integer)
- `offset` (integer)
- `protocol` (string)
- `search` (string)

### `get_service` (~44 tokens)

Get full service detail

Return the full detail row for one service: slug, name, vendor, protocol, category, units, fair price, sources, related services.

Input parameters:

- `slug` (string, required)

### `get_leaderboard` (~63 tokens)

Get a leaderboard slice

Return the top services for one of the canonical leaderboards: cheapest, most_expensive, most_volatile, biggest_drop, biggest_jump, most_observed.

Input parameters:

- `category` (string)
- `kind` (string, required)
- `limit` (integer)

### `recent_observations` (~68 tokens)

Recent observations for a service

Return the most recent price observations for one service, oldest-newest by `observedAt`. Useful when an agent wants to spot intraday trends or audit the inputs to FMV.

Input parameters:

- `limit` (integer)
- `since` (string)
- `slug` (string, required)

### `refuse_if_overpriced` (~77 tokens)

Decide whether to pay a quote

Convenience wrapper agents call right before paying. Returns `should_pay: false` (with a reason and savings estimate) when the quoted amount is materially above ARI's high band; `should_pay: true` otherwise.

Input parameters:

- `amount_usd` (number, required)
- `slug` (string, required)
- `unit` (string)

### `prepay_verdict` (~232 tokens)

Universal pre-payment fairness check

The Universal Fairness Skill entry point. Wraps any agent wallet (Coinbase Agentic Wallet, AgentCash, ATXP, 1Pay.ing, …) with a refuse-to-overpay safety check. Call BEFORE settling any HTTP 402 / x402 / MPP quote. Pass the target URL (or service slug), the quoted amount in micros, the currency (default USD), and the chain (default off-chain). Returns `{ verdict: 'fair' | 'stretched' | 'overpriced' | 'unknown', reason, suggestedMax, evidenceUrl }`. Refuse to settle on `overpriced`; surface the warning and ask consent on `stretched`; settle on `fair`.

Input parameters:

- `amountMicros` (number)
- `amount_micros` (number)
- `chain` (string)
- `currency` (string)
- `service` (string)
- `unit` (string)
- `url` (string, required): The full URL the agent is about to POST/GET against, OR the indexed ARI service slug. The server resolves slug or hostname.

### `verify_receipt` (~65 tokens)

Verify a previously-issued ARI receipt

Re-fetch a receipt by its ULID and re-verify the Ed25519 signature. Use to audit a counterparty's claim, e.g. 'I refused this payment because ARI Receipt 01HZ… said it was overpriced'.

Input parameters:

- `receipt_id` (string, required)

### `get_signed_receipt` (~49 tokens)

Re-fetch a previous signed receipt body

Look up the canonical signed body for a previously-issued receipt id, so an agent can show the exact bytes it relied on when making a payment decision.

Input parameters:

- `for_request_id` (string, required)

### `subscribe_alert` (~92 tokens)

Subscribe to a price alert

Set up a price alert. Pass a webhook URL OR an email. Conditions: `above`, `below`, or `volatility_pct` with a numeric threshold (USD or %). Proxies the existing /api/v1/alerts endpoint.

Input parameters:

- `condition` (string, required)
- `email` (string)
- `slug` (string, required)
- `threshold` (number, required)
- `webhook` (string)

## Diagnostics

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

## Score history

- 2026-08-03: 74
- 2026-08-02: 74
- 2026-08-01: 18
- 2026-07-31: 45
- 2026-07-29: 42
- 2026-07-28: 42
- 2026-07-27: 42

## Links

- npm package: https://www.npmjs.com/package/ari-mcp
- Socket report: https://socket.dev/npm/package/ari-mcp
- Repository: https://github.com/Antmanbuilds/ARI
- Website: https://agentrateindicators.com/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/antmanbuilds-ari-mcp/ari-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/antmanbuilds-ari-mcp/ari-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/antmanbuilds-ari-mcp/ari-mcp