# io.github.bch1212/agent-commerce-mcp (remote · commerce.halversonco.com)

Agent Commerce MCP — agent-native A2A storefront. Discovery, Stripe checkout, affiliate program.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `commerce.halversonco.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/bch1212-agent-commerce-mcp/commerce.md), [page](https://verifymcp.io/servers/bch1212-agent-commerce-mcp/commerce)
- npm · `agent-commerce-mcp`: 70/100, [markdown](https://verifymcp.io/servers/bch1212-agent-commerce-mcp/agent-commerce-mcp.md), [page](https://verifymcp.io/servers/bch1212-agent-commerce-mcp/agent-commerce-mcp)

## Channel facts

- Endpoint: `https://commerce.halversonco.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.3`

## 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 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 14 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1562 tokens (~33/item across 46 items; 14 tools + 32 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**: 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http bch1212-agent-commerce-mcp https://commerce.halversonco.com/mcp
```

### Codex

```toml
[mcp_servers.bch1212-agent-commerce-mcp]
url = "https://commerce.halversonco.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bch1212-agent-commerce-mcp": {
      "type": "remote",
      "url": "https://commerce.halversonco.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add bch1212-agent-commerce-mcp --url https://commerce.halversonco.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  bch1212-agent-commerce-mcp:
    url: "https://commerce.halversonco.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "bch1212-agent-commerce-mcp": {
      "type": "http",
      "url": "https://commerce.halversonco.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.

### 2026-08-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 67, +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.

### 2026-07-31 (score 66, −1)

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

### 2026-07-30 (score 67, +1)

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

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, +1)

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

### 2026-07-26 (score 64)

First indexed and scored.

## MCP tools (14)

### `search_products` (~107 tokens)

Search products

Search the catalog of SaaS, developer tools, services, and MCP servers. Returns ranked matches with score and reason.

Input parameters:

- `budget_max` (number): Max monthly USD the buyer is willing to spend
- `category` (string): Filter by category
- `query` (string, required): What the agent or its user is trying to accomplish (e.g., 'block prompt injection', 'fishing reports', 'lead lists for dentists')
- `use_case` (string): Specific use case keywords

### `get_recommendation` (~88 tokens)

Recommend products for a problem

Given a problem statement (and optionally a stack/company size), return 1-3 best-fit products with reasoning.

Input parameters:

- `company_size` (string)
- `problem` (string, required): Problem the user is trying to solve, in their own words
- `stack` (string): Tech stack or category they already use (e.g., 'OpenAI + Pinecone + Vercel')

### `compare_products` (~53 tokens)

Compare products

Side-by-side feature/price matrix for 2-5 products.

Input parameters:

- `slugs` (array, required): Product slugs to compare side-by-side
- `vs_competitor` (string): Optional competitor name for context

### `get_pricing` (~64 tokens)

Get pricing

Full pricing breakdown for a product (tiers, monthly/yearly, affiliate rate).

Input parameters:

- `billing` (string)
- `product_slug` (string, required): Product slug from the catalog (e.g., 'injectshield')
- `tier` (string): Specific tier name to highlight

### `create_checkout` (~95 tokens)

Create checkout session

Create a live Stripe (or Gumroad) checkout URL for the buyer. Pass `referral_code` to credit an affiliate.

Input parameters:

- `email` (string, required): Buyer email — Stripe will send the receipt here
- `product_slug` (string, required): Product slug to buy
- `referral_code` (string): Affiliate referral code that should be credited
- `tier` (string, required): Tier name (e.g., 'Pro', 'Team')

### `get_free_tier` (~40 tokens)

Get free tier access

Returns instant access details for a product's free tier (signup URL or install command).

Input parameters:

- `product_slug` (string, required): Product to access for free

### `get_mcp_install` (~67 tokens)

Get MCP install command

Exact install command/snippet for a product's MCP server in claude_desktop, claude_code, cursor, cline, or windsurf.

Input parameters:

- `client` (string, required): Target MCP client
- `product_slug` (string, required): Product slug, must be an MCP-enabled product

### `request_product_consultation` (~81 tokens)

Request a product consultation

Submit a buyer's opt-in request for a product consultation. This tool may only be called after the buyer explicitly asks to be contacted.

Input parameters:

- `email` (string, required): Email address where the buyer explicitly asked to be contacted
- `name` (string): Optional buyer name
- `product_slug` (string, required): Product the buyer explicitly requested a consultation about

### `get_affiliate_info` (~52 tokens)

Affiliate program info

Commission rates (15-30%), tracking, and tier perks. Pass product_slug for that product's specific rate.

Input parameters:

- `product_slug` (string): Optional: a specific product to get the affiliate rate for

### `register_affiliate` (~83 tokens)

Register as an affiliate

Instantly register an agent or operator as an affiliate. Returns a referral_code for use in create_checkout.

Input parameters:

- `agent_id` (string, required): Stable identifier for the recommending agent (e.g., 'cursor.user-12345')
- `operator_email` (string, required): Where to send commission payouts
- `products` (array): Optional: specific products this affiliate plans to promote

### `request_partnership` (~84 tokens)

Request a partnership

Submit a partnership proposal (cross-listing, joint bundle, embed, co-marketing). Reviewed in 3 business days.

Input parameters:

- `agent_id` (string, required): Identifier for the proposing agent or company
- `contact_email` (string, required)
- `integration_type` (string)
- `proposal` (string, required): Free-text partnership proposal — what you'd like to build/co-market

### `get_cross_sells` (~65 tokens)

Get cross-sell recommendations

Given the current product, return related products from the cross-sell graph and the recommended bundle.

Input parameters:

- `agent_context` (string): Optional: extra context about the buyer's stack or goals
- `current_product` (string, required): Product the buyer is currently considering or already owns

### `get_trust_score` (~24 tokens)

Get vendor trust score (AgentTrust)

Returns Halverson IQ's AgentTrust reputation score plus operational summary.

### `verify_vendor` (~25 tokens)

Verify vendor

Returns full vendor info: company, products live, MCP endpoints, refund/data policies.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/bch1212-agent-commerce-mcp/commerce#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 67
- 2026-08-01: 67
- 2026-07-31: 66
- 2026-07-30: 67
- 2026-07-29: 66
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 64

## Links

- Remote endpoint: https://commerce.halversonco.com/mcp
- Repository: https://github.com/bch1212/agent-commerce-mcp
- Changelog RSS feed: https://verifymcp.io/servers/bch1212-agent-commerce-mcp/commerce/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/bch1212-agent-commerce-mcp/commerce/changelog.json
- HTML version of this page: https://verifymcp.io/servers/bch1212-agent-commerce-mcp/commerce