# AI Commerce Intelligence (remote · mcp.agentcommerceexchange.com)

Shopify product discovery and x402-paid offer verification for AI agents.

- Trust score: 18/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.agentcommerceexchange.com`: 18/100 (this document), [markdown](https://verifymcp.io/servers/workhard1011-ai-commerce-intelligence/mcp.md), [page](https://verifymcp.io/servers/workhard1011-ai-commerce-intelligence/mcp)

## Channel facts

- Endpoint: `https://mcp.agentcommerceexchange.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.9.1`

## 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 2026-09-20.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 404, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 404.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the AI Commerce Intelligence MCP server?

AI Commerce Intelligence is a hosted endpoint at https://mcp.agentcommerceexchange.com/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 workhard1011-ai-commerce-intelligence 'https://mcp.agentcommerceexchange.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "workhard1011-ai-commerce-intelligence": {
      "url": "https://mcp.agentcommerceexchange.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "workhard1011-ai-commerce-intelligence": {
      "type": "http",
      "url": "https://mcp.agentcommerceexchange.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.workhard1011-ai-commerce-intelligence]
url = "https://mcp.agentcommerceexchange.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "workhard1011-ai-commerce-intelligence": {
      "type": "remote",
      "url": "https://mcp.agentcommerceexchange.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add workhard1011-ai-commerce-intelligence --url 'https://mcp.agentcommerceexchange.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  workhard1011-ai-commerce-intelligence:
    url: "https://mcp.agentcommerceexchange.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "workhard1011-ai-commerce-intelligence": {
      "Transport": "http",
      "Url": "https://mcp.agentcommerceexchange.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add workhard1011-ai-commerce-intelligence -t streamable-http -u 'https://mcp.agentcommerceexchange.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "workhard1011-ai-commerce-intelligence": {
      "type": "http",
      "url": "https://mcp.agentcommerceexchange.com/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.

### 2026-09-08 (score 18, −41)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.23 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-06 (score 59, +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.

### 2026-09-05 (score 58, 0)

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

### 2026-09-04 (score 58, +1)

- [cosmetic] “commerce_preflight” added an optional parameter “region”
- [cosmetic] “ace_check” added an optional parameter “language”
- [cosmetic] “ace_check” added an optional parameter “postal_code”
- [cosmetic] “ace_check” added an optional parameter “region”
- [cosmetic] “commerce_preflight” added an optional parameter “language”
- [cosmetic] “commerce_preflight” added an optional parameter “postal_code”

### 2026-09-03 (score 57, 0)

- [security] Tool “commerce_preflight” rewrote its description, which is the text the model reads
- [security] Tool “commercial_attribution_policy” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 980 → 1092
- [functional] Server version: 4.0 → 5.0
- [functional] New tool “route_commerce_decision”
- [functional] New tool “commerce_trust_network”

### 2026-09-02 (score 57, +2)

- [security] The server changed its declared name: AI Commerce Intelligence → Agent Commerce Exchange
- [security] Tool “commerce_capabilities” rewrote its description, which is the text the model reads
- [security] Tool “product_discovery” rewrote its description, which is the text the model reads
- [security] Tool “service_pricing” rewrote its description, which is the text the model reads
- [security] Tool “verify_global_offer” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 45 → 75
- [functional] Schema quality: fair → good
- [functional] Server version: 0.9.1 → 4.0
- [functional] New tool “ace_check”
- [functional] New tool “commerce_preflight”
- [functional] New tool “commerce_trust_graph”
- [functional] New tool “commercial_attribution_policy”
- [functional] New tool “compile_commerce_claims”
- [functional] New tool “create_commerce_referral”
- [functional] New tool “merchant_readiness”
- [functional] New tool “regulatory_recall_lookup”
- [functional] New tool “resolve_product_identity”
- [cosmetic] “product_discovery” added an optional parameter “providers”

### 2026-09-01 (score 55, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-31 (score 55)

First indexed and scored.

## MCP tools (15)

### `commerce_capabilities` (~31 tokens)

Describe ACE: a read-only commerce discovery, ACE Check, and pre-purchase verification service for AI agents.

### `service_pricing` (~18 tokens)

Return machine-readable ACE prices and usage boundaries.

### `product_discovery` (~92 tokens)

Search the ACE Provider Mesh just in time. Shopify Global Catalog is live; eBay Browse and Amazon Creators join only when their explicit authorization gates are open.

Input parameters:

- `country` (string)
- `currency` (string)
- `limit` (integer)
- `max_price` (number)
- `min_price` (number)
- `providers` (array)
- `query` (string, required)

### `compile_commerce_claims` (~47 tokens)

Convert high-confidence natural-language commerce requirements into reviewable structured ACE claims. This tool does not verify the claims and never turns a suggestion into truth.

Input parameters:

- `query` (string, required)

### `ace_check` (~188 tokens)

Free bounded ACE Check. ACE Check remains the product-level decision surface (APPROVE/REJECT/UNKNOWN) while each structured claim receives PROVED/CONTRADICTED/SOURCE_CONFLICT/STALE/VERIFY_MORE/UNVERIFIABLE. Legacy required_terms remain supported.

Input parameters:

- `auto_compile_claims` (boolean)
- `candidate_ids` (array)
- `claims` (array)
- `country` (string)
- `currency` (string)
- `excluded_terms` (array)
- `language` (string)
- `limit` (integer)
- `max_price` (number)
- `min_price` (number)
- `postal_code` (string)
- `preferred_terms` (array)
- `providers` (array)
- `query` (string)
- `region` (string)
- `required_terms` (array)

### `resolve_product_identity` (~62 tokens)

Resolve provider-qualified candidate IDs into conservative ACE product entities. Exact GTIN or exact brand+MPN may bridge providers; title similarity alone never merges products and variant conflicts block cross-source proof.

Input parameters:

- `candidate_ids` (array, required)
- `country` (string)

### `regulatory_recall_lookup` (~70 tokens)

Query the authorized U.S. CPSC recall API by an exact GTIN/UPC. Results are exact-identifier post-filtered. A recall match is authoritative safety evidence; no match is UNKNOWN and never proof that a product is safe or not recalled elsewhere.

Input parameters:

- `gtin` (string, required)

### `commerce_trust_graph` (~70 tokens)

Build a bounded multi-source ACE Trust Graph from authorized provider-qualified candidate IDs. Evidence may cross providers only through an explicit strong product-identity bridge and never for provider-bound offer/policy claims.

Input parameters:

- `candidate_ids` (array, required)
- `claims` (array)
- `country` (string)

### `merchant_readiness` (~91 tokens)

Summarize represented ACE eligibility and evidence gaps across up to five provider-qualified merchant candidates. This is a bounded readiness sample, not a claimed full-catalog lost-revenue estimate.

Input parameters:

- `candidate_ids` (array, required)
- `claims` (array)
- `country` (string)
- `excluded_terms` (array)
- `preferred_terms` (array)
- `required_terms` (array)

### `commercial_attribution_policy` (~48 tokens)

Describe the v4 commercial attribution rules preserved by ACE v5.0. Commercial relationships and commissions can never alter ACE Check, ACE Verdict, claim status, source authority, or organic truth.

### `create_commerce_referral` (~66 tokens)

Create an ACE referral from a short-lived server-side decision_ref returned by ACE Check. Caller-supplied Verdicts are never accepted as commercial eligibility proof.

Input parameters:

- `decision_ref` (string, required)
- `event_id` (string)
- `record_click` (boolean)

### `commerce_trust_network` (~39 tokens)

Return the public ACE Commerce Trust Network manifest: participants, protocol interoperability state, extension points, and the rule that network membership never grants truth authority.

### `route_commerce_decision` (~68 tokens)

Plan execution routes for a short-lived server-issued ACE decision_ref. Routing is strictly post-truth: it cannot change product ranking or ACE Verdict and only exposes protocol paths that are actually verified as executable.

Input parameters:

- `decision_ref` (string, required)
- `preferred_protocols` (array)

### `commerce_preflight` (~195 tokens)

ACE's flagship pre-purchase decision product. ACE Verdict remains APPROVE/REJECT/UNKNOWN while v5.0 preserves universal claims through explicit product identity and field-level source trust. Batch-refreshes up to five finalists, preserves conflicts/staleness/unverifiable claims, and never treats query wording as proof.

Input parameters:

- `auto_compile_claims` (boolean)
- `candidate_ids` (array)
- `claims` (array)
- `country` (string)
- `currency` (string)
- `excluded_terms` (array)
- `finalist_limit` (integer)
- `language` (string)
- `max_price` (number)
- `min_price` (number)
- `postal_code` (string)
- `preferred_terms` (array)
- `providers` (array)
- `query` (string)
- `region` (string)
- `required_terms` (array)

### `verify_global_offer` (~54 tokens)

Low-level compatibility primitive. Resolve a Shopify Global Catalog product/variant ID or HTTPS product URL to current normalized offers. New integrations should prefer commerce_preflight.

Input parameters:

- `country` (string)
- `identifier` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/workhard1011-ai-commerce-intelligence/mcp#diagnostics

## Score history

- 2026-09-20: 18
- 2026-09-19: 18
- 2026-09-18: 18
- 2026-09-17: 18
- 2026-09-16: 18
- 2026-09-15: 18
- 2026-09-14: 18
- 2026-09-13: 18
- 2026-09-12: 18
- 2026-09-11: 18
- 2026-09-10: 18
- 2026-09-09: 18
- 2026-09-08: 18
- 2026-09-07: 59
- 2026-09-06: 59
- 2026-09-05: 58
- 2026-09-04: 58
- 2026-09-03: 57
- 2026-09-02: 57
- 2026-09-01: 55
- 2026-08-31: 55

## Common questions

### What is the AI Commerce Intelligence MCP server?

AI Commerce Intelligence is an MCP server listed in the public MCP registry as io.github.workhard1011/ai-commerce-intelligence. Shopify product discovery and x402-paid offer verification for AI agents. This page covers its hosted endpoint (https://mcp.agentcommerceexchange.com/mcp).

### Is the AI Commerce Intelligence MCP server safe to use?

AI Commerce Intelligence scores 18 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 AI Commerce Intelligence MCP server expose?

AI Commerce Intelligence exposes 15 tools: commerce_capabilities, service_pricing, product_discovery, compile_commerce_claims, ace_check, and 10 more. Their descriptions and schemas cost roughly 1,139 tokens of context every time the server is loaded.

### Does the AI Commerce Intelligence MCP server require authentication?

No. We connected to AI Commerce Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AI Commerce Intelligence MCP server still maintained?

AI Commerce Intelligence 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.

## Links

- Remote endpoint: https://mcp.agentcommerceexchange.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/workhard1011-ai-commerce-intelligence/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/workhard1011-ai-commerce-intelligence/mcp.json
- HTML version of this page: https://verifymcp.io/servers/workhard1011-ai-commerce-intelligence/mcp