# ARC: agent checkout reachability (remote · www.arcreport.ai)

Free, no sign-in MCP: can AI agents reach checkout at a store? Try: Use ARC to check allbirds.com

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `www.arcreport.ai`: 78/100 (this document), [markdown](https://verifymcp.io/servers/ai-arcreport-mcp/api-mcp.md), [page](https://verifymcp.io/servers/ai-arcreport-mcp/api-mcp)

## Channel facts

- Endpoint: `https://www.arcreport.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `2.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-10-18.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3057 tokens (~160/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 20 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 ARC: agent checkout reachability MCP server?

ARC: agent checkout reachability is a hosted endpoint at https://www.arcreport.ai/api/mcp, so there is nothing to install locally. 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 --transport http ai-arcreport-mcp 'https://www.arcreport.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-arcreport-mcp": {
      "url": "https://www.arcreport.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-arcreport-mcp": {
      "type": "http",
      "url": "https://www.arcreport.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-arcreport-mcp]
url = "https://www.arcreport.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-arcreport-mcp": {
      "type": "remote",
      "url": "https://www.arcreport.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-arcreport-mcp --url 'https://www.arcreport.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-arcreport-mcp:
    url: "https://www.arcreport.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-arcreport-mcp": {
      "Transport": "http",
      "Url": "https://www.arcreport.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-arcreport-mcp -t streamable-http -u 'https://www.arcreport.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-arcreport-mcp": {
      "type": "http",
      "url": "https://www.arcreport.ai/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-10-18 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 77, 0)

- [security] Tool “can_agent_checkout” rewrote its description, which is the text the model reads

### 2026-10-16 (score 77, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “can_agent_checkout” rewrote its description, which is the text the model reads
- [security] Tool “check_agent_readiness” rewrote its description, which is the text the model reads
- [security] Tool “get_readiness_result” rewrote its description, which is the text the model reads
- [security] Tool “list_monitors” rewrote its description, which is the text the model reads

### 2026-10-15 (score 77, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “can_agent_checkout” rewrote its description, which is the text the model reads
- [security] Tool “check_store” rewrote its description, which is the text the model reads
- [security] Tool “find_stores” rewrote its description, which is the text the model reads

### 2026-10-14 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “report_checkout” rewrote its description, which is the text the model reads

### 2026-10-13 (score 76, −1)

- [security regression] Authorization: pass → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “ask_agents_about_brand” rewrote its description, which is the text the model reads
- [security] Tool “bulk_create_monitors” rewrote its description, which is the text the model reads
- [security] Tool “can_agent_checkout” rewrote its description, which is the text the model reads
- [security] Tool “check_agent_readiness” rewrote its description, which is the text the model reads
- [security] Tool “check_store” rewrote its description, which is the text the model reads
- [security] Tool “find_stores” rewrote its description, which is the text the model reads
- [security] Tool “get_fixes” rewrote its description, which is the text the model reads
- [security] Tool “get_readiness_result” rewrote its description, which is the text the model reads
- [security] Tool “get_store_hub” rewrote its description, which is the text the model reads
- [security] Tool “google_checkout_readiness” rewrote its description, which is the text the model reads
- [security] Tool “list_monitors” rewrote its description, which is the text the model reads
- [security] Tool “list_readiness_checks” rewrote its description, which is the text the model reads
- [security] Tool “monitor_summary” rewrote its description, which is the text the model reads
- [security] Tool “pause_monitor” rewrote its description, which is the text the model reads
- [security] Tool “resume_monitor” rewrote its description, which is the text the model reads
- [security] Tool “run_monitor_now” rewrote its description, which is the text the model reads
- [security] Tool “update_monitor” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 139 → 155
- [functional improvement] Stability: unverified → 0.03
- [functional] The server now declares the “prompts” capability
- [functional] The server now declares the “resources” capability
- [functional] New tool “report_checkout”

### 2026-10-12 (score 77)

First indexed and scored.

## MCP tools (19)

### `check_store` (~106 tokens)

Check if an AI agent can reach checkout on a store before trying. Call this with a store domain, such as allbirds.com. Returns the saved checkout evidence, or not checked yet when ARC has no saved check. Free, no login, no new scan, and no fetch of the store. A missing field says "not recorded" and is not a zero. Results are advisory. ARC stops before payment.

Input parameters:

- `domain` (string, required): Store domain, such as allbirds.com.

### `find_stores` (~165 tokens)

Find stores where a saved check shows an AI agent can reach checkout. Filter by platform, protocol, or category. With no filters, returns the most recently checked of those stores and labels the result default: no filters given. A missing result is not counted against a store. No login and no new scan. Results are advisory. ARC stops before payment.

Input parameters:

- `category` (string): Category or shopper words, such as footwear or running shoes.
- `limit` (integer): How many stores to return. Default 10. Maximum 25.
- `platform` (string): Commerce platform id, such as shopify or woocommerce.
- `protocol` (string): ucp, webmcp, or mcp. ACP, PAP, and payments are not recorded per store.

### `report_checkout` (~250 tokens)

Report how far one agent got at one store. Free, no login. Omit contributor_key and ARC issues one. Emails, phones, street addresses, card numbers, IP addresses, and private hosts are rejected. The report stays private until 3 independent contributors with a day-old key, or enough reputation, agree within 14 days. A blocked outcome also waits for ARC's free HTTP recheck. Same as POST /api/outcomes.

Input parameters:

- `agent_family` (string, required): Agent family, such as browser or a model family. No personal name.
- `agent_name` (string, required): Name of the agent that tried the checkout. No personal name.
- `blocker` (string, required): What stopped the agent, or none.
- `contributor_key` (string): Optional. Omit it and ARC returns a free key. Send that key on later reports.
- `furthest_step` (string, required): Furthest step the agent reached.
- `store_domain` (string, required): Store hostname, such as allbirds.com.
- `store_error_text` (string): Optional store error text. Personal data is stripped.
- `timestamp` (string, required): ISO 8601 time of the attempt, within the last 14 days.

### `get_store_hub` (~55 tokens)

[Requires sign-in] Look up a free ARC store card by host. Includes saved measurements and brand_claim ownership metadata. Brand statements are not measured by ARC; claims never change measured scores.

Input parameters:

- `host` (string, required)

### `google_checkout_readiness` (~64 tokens)

[Requires sign-in] Read saved public Google agentic checkout readiness checks for a store. Free; no new scan or paid calls. Merchant Center feed eligibility cannot be checked from outside. Not Google approval or certification.

Input parameters:

- `host` (string, required): Store host or URL

### `product_data_check` (~62 tokens)

Free latest saved product data and return/shipping policy check from the store's pages and structured data. Reads history only; no store fetch or model call. A missing result is not a zero.

Input parameters:

- `host` (string)
- `url` (string)

### `can_agent_checkout` (~130 tokens)

[Requires sign-in] Call when you need a saved checkout-link check for any public store URL, not only Index brands. Saved HTTP checkout check for a public homepage or product URL: catalog, product, checkout link, UCP profile, blocks, and one fix. No model call, payment, or browser scan. Uses ARC's last check (cached up to 24 hours). A missing result is unknown, not a no. A checkout link means reach checkout, not a completed order. Results are advisory. ARC stops before payment.

Input parameters:

- `url` (string, required): Public store homepage or product URL

### `check_agent_readiness` (~157 tokens)

[Requires sign-in] Check whether personal AI agents can reach a product URL, understand it, and reach checkout. Runs ARC's readiness check: crawler access, whether an agent can answer a shopper's questions from the page, and personal shopping agents trying to add to cart or reach checkout. Returns a check id — poll get_readiness_result (about 30–60 seconds). This does not ask what agents think of the brand; use ask_agents_about_brand for that.

Input parameters:

- `task` (string): Optional goal, e.g. 'add to cart' (default) or 'reach checkout'.
- `url` (string, required): The product or store URL to test, e.g. https://store.com/products/best-seller

### `get_readiness_result` (~116 tokens)

[Requires sign-in] Get a readiness check by id. While running, reports progress. When complete, reports whether personal agents could reach the page, understand it, and reach checkout, plus the wall, concrete next steps, a directional score, a per-agent breakdown, and screenshots. Calling this again with the same id redisplays the result and does not start a new check. Never re-run check_agent_readiness just to see the screenshots again.

Input parameters:

- `id` (string, required): The check id returned by check_agent_readiness.

### `list_readiness_checks` (~52 tokens)

[Requires sign-in] List this workspace's recent readiness checks (newest first) — each store, its score, status, and id. Use an id with get_readiness_result to reopen a check.

### `ask_agents_about_brand` (~283 tokens)

[Requires sign-in] Ask benchmark personal-agent personas what they think of a brand and whether they would recommend it for a category. Personas: Muse-style, Instinct-style, Grok Bot-style, OpenAI dots-style, and OpenClaw-style. This tool uses benchmark personas, including the Grok Bot-style persona; these are not live consumer-product sessions. It is not the real Grok read-back on a scan and it is not the agent-rails HTTP check. What Grok tells shoppers on a scan is a real model call via API, checked against the store's pages, not the consumer Grok app. All five cart attempts, Grok included, are ARC browser cart tests. Returns, per persona: mentioned, recommended, which competitors were recommended instead, sentiment, and short quotes, plus next steps. Limited to 8 runs per workspace per day and 12 per network. Free workspaces also share a site-wide daily cap so unpaid runs cannot drain the model budget.

Input parameters:

- `brand` (string, required): Brand name, e.g. Allbirds.
- `category` (string, required): Product category a shopper would ask about, e.g. running shoes.
- `competitors` (array): Optional competitor brand names to watch for in the answers.
- `store_url` (string, required): Public store URL, e.g. https://www.allbirds.com

### `get_fixes` (~177 tokens)

[Requires sign-in] Concrete next steps to get recommended by personal agents and to become reachable, understandable, and buyable. Pass a readiness check id and/or the brand, category, store URL, and competitors that were recommended instead. Uses the check's evidence when an id is given. Does not start a new check.

Input parameters:

- `brand` (string): Brand name, if you want recommendation steps.
- `category` (string): Product category, e.g. running shoes.
- `competitors_recommended` (array): Competitors personal agents recommended instead.
- `mentioned` (boolean): Whether any benchmark persona mentioned the brand.
- `recommended` (boolean): Whether any benchmark persona recommended the brand for the category.
- `scan_id` (string): Optional readiness check id from check_agent_readiness.
- `store_url` (string): Store URL.

### `bulk_create_monitors` (~263 tokens)

[Requires sign-in] Set up scheduled monitoring for one or more store URLs (the 'set up monitoring' flow). Validates each URL and rejects invalid/private/internal ones. GUIDED FLOW: first ask the user for the URLs (paste a list or a CSV), then the frequency (daily/weekly/monthly, default weekly). Every plan runs the core panel of personal shopping agents — no picking needed. Call once without confirmed=true to preview the exact setup and scan-credit estimate, read that summary to the user, and only after the user explicitly says yes call again with confirmed=true to create the monitors. Each scheduled run uses one scan credit. Every run emails who reached the cart, who stopped or started, the stuck step, and the fix. Weekly is what the plans include; daily only fits when the plan's scan allowance covers it.

Input parameters:

- `confirmed` (boolean): Must be true only after the user has confirmed the summarized setup. If missing or false, ARC returns a preview and creates nothing.
- `depth` (string): How far each scan goes. Default: cart.
- `frequency` (string): How often to re-test. Default: weekly.
- `urls` (array, required): Store/product URLs to monitor (a list or pasted CSV lines).

### `list_monitors` (~56 tokens)

[Requires sign-in] List the workspace's monitors — each store re-checked on a schedule for whether personal agents can still reach it and its checkout. Includes cadence, status, last score, next run, and the monitor id.

### `monitor_summary` (~41 tokens)

[Requires sign-in] Overview of whether monitored stores are still buyable by personal agents: latest score, trend, status, next run, and recent regression alerts.

### `update_monitor` (~64 tokens)

[Requires sign-in] Change a monitor's cadence (daily/weekly/monthly) or label. Use the monitor id from list_monitors.

Input parameters:

- `frequency` (string)
- `id` (string, required): Monitor id from list_monitors.
- `label` (string)

### `pause_monitor` (~50 tokens)

[Requires sign-in] Pause a monitor so it stops running on schedule (its history is kept). Use the monitor id from list_monitors.

Input parameters:

- `id` (string, required): Monitor id from list_monitors.

### `resume_monitor` (~31 tokens)

[Requires sign-in] Resume a paused monitor.

Input parameters:

- `id` (string, required): Monitor id from list_monitors.

### `run_monitor_now` (~71 tokens)

[Requires sign-in] Run a monitor's scan immediately (off-schedule) to establish or refresh its baseline. Consumes one scan credit — only call when the user explicitly asks to run now. Use the monitor id from list_monitors.

Input parameters:

- `id` (string, required): Monitor id from list_monitors.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-arcreport-mcp/api-mcp#diagnostics

## Score history

- 2026-10-18: 78
- 2026-10-17: 77
- 2026-10-16: 77
- 2026-10-15: 77
- 2026-10-14: 76
- 2026-10-13: 76
- 2026-10-12: 77

## Common questions

### What is the ARC: agent checkout reachability MCP server?

ARC: agent checkout reachability is an MCP server listed in the public MCP registry as ai.arcreport/mcp. Free, no sign-in MCP: can AI agents reach checkout at a store? Try: Use ARC to check allbirds.com. This page covers its hosted endpoint (https://www.arcreport.ai/api/mcp).

### Is the ARC: agent checkout reachability MCP server safe to use?

ARC: agent checkout reachability scores 78 out of 100 on VerifyMCP. 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 ARC: agent checkout reachability MCP server expose?

ARC: agent checkout reachability exposes 19 tools: check_store, find_stores, report_checkout, get_store_hub, google_checkout_readiness, and 14 more. Their descriptions and schemas cost roughly 2,193 tokens of context every time the server is loaded.

### Does the ARC: agent checkout reachability MCP server require authentication?

Yes. ARC: agent checkout reachability asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the ARC: agent checkout reachability MCP server still maintained?

ARC: agent checkout reachability is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.arcreport.ai/api/mcp
- Repository: https://github.com/abab7575/arc-mcp
- Website: https://www.arcreport.ai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-arcreport-mcp/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-arcreport-mcp/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-arcreport-mcp/api-mcp