Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Ivory River — Agent Commerce

REMOTE · MCP.IVORYRIVER.STORE · SCANNED SEP 20

Search, configure, quote, recommend gaming PCs and components. Hands user to in-browser checkout.

+50 this week 68 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security46
Transport & Reachability40
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 766 tokens (~95/item across 8 items; 8 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage91
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 73% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Ivory River — Agent Commerce MCP server?

Ivory River — Agent Commerce is a hosted endpoint at https://mcp.ivoryriver.store/sse, 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.

remote · mcp.ivoryriver.store

# add to Claude Code
claude mcp add --transport http store-ivoryriver-agent-commerce 'https://mcp.ivoryriver.store/sse'
// .cursor/mcp.json
{
  "mcpServers": {
    "store-ivoryriver-agent-commerce": {
      "url": "https://mcp.ivoryriver.store/sse"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "store-ivoryriver-agent-commerce": {
      "type": "http",
      "url": "https://mcp.ivoryriver.store/sse"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.store-ivoryriver-agent-commerce]
url = "https://mcp.ivoryriver.store/sse"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "store-ivoryriver-agent-commerce": {
      "type": "remote",
      "url": "https://mcp.ivoryriver.store/sse",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add store-ivoryriver-agent-commerce --url 'https://mcp.ivoryriver.store/sse' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  store-ivoryriver-agent-commerce:
    url: "https://mcp.ivoryriver.store/sse"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "store-ivoryriver-agent-commerce": {
      "Transport": "http",
      "Url": "https://mcp.ivoryriver.store/sse"
    }
  }
}
# add to Vellum
assistant mcp add store-ivoryriver-agent-commerce -t streamable-http -u 'https://mcp.ivoryriver.store/sse'
// mcp.json
{
  "mcpServers": {
    "store-ivoryriver-agent-commerce": {
      "type": "http",
      "url": "https://mcp.ivoryriver.store/sse"
    }
  }
}

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

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Sept 26 +50
    • Injection markers: unverified → pass security
    • Stability: unverified → pass security
    • Transport: fail → pass security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • Endpoint reachability: not serving MCP → reachable functional
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
  • 3 Sept 26 −46
    • Endpoint reachability: reachable → not serving MCP security
    • HTTPS: unverified → fail security
    • Stability: pass → unverified security
    • Tool safety: pass → unverified 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. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
  • 2 Sept 26 +46
    • HTTPS: fail → unverified security
    • Injection markers: unverified → pass security
    • Stability: unverified → pass security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • Endpoint reachability: not serving MCP → reachable functional
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
  • 1 Sept 26 0
    • HTTPS: unverified → fail security
  • 31 Aug 26 −46
    • Endpoint reachability: reachable → not serving MCP security
    • HTTPS: fail → unverified security
    • Stability: pass → unverified security
    • Tool safety: pass → unverified 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. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
  • 30 Aug 26 +46
    • Injection markers: unverified → pass security
    • Stability: unverified → pass security
    • First check of Judged manipulation: pass security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • Endpoint reachability: not serving MCP → reachable functional
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
    • First check of Destructive annotations: pass functional
  • 27 Aug 26 0
    • Endpoint reachability: reachable → not serving MCP security
  • 26 Aug 26 −49
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://mcp.ivoryriver.store/sse

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=ivoryriver.store CN=YE1,O=Let's Encrypt,C=US 13 Aug 2026 11 Nov 2026 ECDSA 256 ECDSA-SHA384 5f7748ab1e8f039b207a7e07e651119a0e2
SANs: *.ivoryriver.store, ivoryriver.store
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.ivoryriver.store. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
store. present 2327 13 Verified
ivoryriver.store. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 404
Header Value
content-security-policy default-src 'none'
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
sse https://mcp.ivoryriver.store/sse Verified 200
http (plaintext) http://mcp.ivoryriver.store/sse Served over HTTP 200
MCP tools · 8 exposed · ~766 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_compatibility ~63

Pairwise socket / DDR / form-factor compatibility check between two products. Returns { compatible, reason }. Use before recommending a CPU + motherboard pairing or RAM + motherboard.

NameTypeReqDescription
product_id_1integeryes
product_id_2integeryes

No output schema declared.

No examples provided.

get_aivy_handoff_link ~215

Build the URL the agent hands to the user to finalize a recommendation. Lands the user on ivoryriver.store with the chat widget auto-opened, the agent's recommendation pre-staged, and quick-reply chips: [Yes, add to cart] [Show me the breakdown] [Modify components]. Use this AFTER you've recommended a build (via recommend_build / list_build_options / quote_build) and the user wants to proceed. The user always finishes the purchase in the browser; you never check out.

NameTypeReqDescription
agent_namestringHow the agent should be named in the handoff greeting (e.g. "Claude Desktop", "Cursor", "your AI assistant"). Cosmetic; defaults to "your AI assistant".
contextstringOptional one-line summary of what the user originally asked (e.g. "streaming + 4K editing under $2K"). Shown to the chat backend so Aivy understands the original ask.
recommendationobjectyesThe recommendation to hand off.

No output schema declared.

No examples provided.

get_product ~61

Get full detail for a single product by ID. Includes price, stock, attributes, and (for BYOPC builds) a configurator summary.

NameTypeReqDescription
fieldsstringOptional comma-separated field projection.
idintegeryesWooCommerce product ID.

No output schema declared.

No examples provided.

list_build_options ~97

Pull the full configurator schema for a single BYOPC tier: every field (Processor, Motherboard, GPU, RAM, Storage, etc.) with all child product options including price, stock, and IDs. Use this to see what selections are available before quoting.

NameTypeReqDescription
tier_idintegeryesBYOPC tier product ID. 378 Squire, 459 Knight, 371 DragonSlayer, 460 Archangel.

No output schema declared.

No examples provided.

list_builds ~54

List the four BYOPC tiers (Squire, Knight, DragonSlayer, Archangel) with their base prices and aggregate component summaries. Use this to overview what custom-build options exist before drilling into a specific tier.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

quote_build ~92

Itemize a configured BYOPC build: returns line totals + grand total + pairwise compatibility check. Empty selections are valid -- the server auto-fills the cheapest in-stock option for any required field.

NameTypeReqDescription
selectionsobjectObject mapping field_id (string) → child_product_id (integer). E.g. {"123": 456, "789": 101}.
tier_idintegeryes

No output schema declared.

No examples provided.

recommend_build ~99

Recommend BYOPC desktop tiers, optionally filtered by budget. `use_case` is informational (echoed in metadata) and helps the agent reason; the result is sorted by total ascending. For laptop recommendations, call search_products with category="laptops" instead.

NameTypeReqDescription
budgetnumberUSD ceiling. Builds with total > budget are dropped.
use_casestringFree-form e.g. "competitive FPS gaming", "video editing".

No output schema declared.

No examples provided.

search_products ~85

Search the Ivory River catalog with semantic + keyword hybrid ranking. Use for natural-language queries like "rtx 5090 laptop under $3000" or "case for AM5 build with tempered glass".

NameTypeReqDescription
in_stockbooleanWhether to exclude out-of-stock items. Default true.
limitinteger
querystringyesFree-text search query.

No output schema declared.

No examples provided.

Common questions

What is the Ivory River — Agent Commerce MCP server?

Ivory River — Agent Commerce is an MCP server listed in the public MCP registry as store.ivoryriver/agent-commerce. Search, configure, quote, recommend gaming PCs and components. Hands user to in-browser checkout. This page covers its hosted endpoint (https://mcp.ivoryriver.store/sse).

Is the Ivory River — Agent Commerce MCP server safe to use?

Ivory River — Agent Commerce scores 68 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 Ivory River — Agent Commerce MCP server expose?

Ivory River — Agent Commerce exposes 8 tools: search_products, get_product, list_builds, list_build_options, quote_build, and 3 more. Their descriptions and schemas cost roughly 766 tokens of context every time the server is loaded.

Does the Ivory River — Agent Commerce MCP server require authentication?

No. We connected to Ivory River — Agent Commerce without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Ivory River — Agent Commerce MCP server still maintained?

Ivory River — Agent Commerce 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.