CPG Knowledge Graph (MCP) is a remote MCP server that gives an AI agent 14 tools, among them check_eligibility, count_gtin_coverage, find_makers. It answers at https://mcp.cpgknowledgegraph.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
The CPG Knowledge Graph with SPARKS, served live over MCP by GreenCore Solutions Corp. — the execution layer the STANDARD-10060 reference supports.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_eligibility | Check whether a GTIN can ship to a specific retailer banner in a country. Inputs: gtin, banner, country_iso |
count_gtin_coverage | Global coverage statistics: GTINs, nodes, makers (supply), retailers (demand). |
find_makers | Global cross-node maker (supply) search. Filter by segment / region / node / has_website. Inputs: segment, region, node, has_website, limit |
find_retailers | Global cross-node retailer (demand) search. Filter by region / node / parent_banner. Inputs: region, node, parent_banner, limit |
get_kernel | SPARKS completeness tier for a brand in a market: 100 = resolvable (a real pack/size record is held) . 8 = registered (brand known, pack/size pending) . 'floor' = STANDARD default (no brand-specific record). Returns the stored tier flag — d Inputs: brand, node |
get_signal_chain | Return the full ACM-68000 signal chain for a GTIN (zero-pads to 14). Inputs: gtin |
list_brands_by_node | SPARKS depth surface: the distinct brands SPARKS covers in a sovereign market. Answers 'what brands do you know in [node]'. Coverage only — no pack/size values. Inputs: node |
list_nodes | The 49 sovereign nodes (the spine) — each with its GS1 GTIN and CLEAN per-node maker (supply) and retailer (demand) counts (separate subqueries, never summed). |
list_sku_types | SPARKS taxonomy: the 84 standing BPC product-type codes the graph is structured on. Validate a type against this before a typed query. (BRAND is a tier, not a type.) |
node_market | Supply↔demand bridge for ONE jurisdiction: makers (supply) and retailers (demand) as two separate counts (never summed), plus the same-node potential bridge pairs. Inputs: code |
resolve_gtin | Resolve a GTIN to its procurement readiness signal. Zero-pads input to 14 digits. Inputs: gtin |
resolve_node | Resolve one node: its GS1 license + its makers (supply) + its retailers (demand). Inputs: code |
resolve_scope | GSC Scoped Agents Registry — Era 1 founding registry (1,000,000 standing) plus Era 2 station-keyed registry (1,000,000 capacity, mint-on-activation) under SM-ECO-10060. Inputs: scope_id |
resolve_sparks | Two-branch SPARKS resolver (zero-pads GTIN to 14). Branch A GSC Territory/License GTIN (990832300xxx) -> FULL license record (public). Branch B any third-party BPC GTIN -> GATED proof {recognized, region_node, kernel_available}; the pack/si Inputs: gtin |
Every block below points at https://mcp.cpgknowledgegraph.ai/mcp. Pick your client and copy.
claude mcp add --transport http cpg-knowledge-graph-mcp https://mcp.cpgknowledgegraph.ai/mcp
{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.cpgknowledgegraph.ai/mcp"]
}
}
}{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"url": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}{
"servers": {
"cpg-knowledge-graph-mcp": {
"type": "http",
"url": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}{
"context_servers": {
"cpg-knowledge-graph-mcp": {
"url": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"serverUrl": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"url": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}name: CPG Knowledge Graph (MCP)
version: 0.0.1
schema: v1
mcpServers:
- name: CPG Knowledge Graph (MCP)
type: streamable-http
url: https://mcp.cpgknowledgegraph.ai/mcp{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"httpUrl": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"type": "http",
"url": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}{
"mcpServers": {
"cpg-knowledge-graph-mcp": {
"url": "https://mcp.cpgknowledgegraph.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.cpgknowledgegraph.ai%2Fmcp&type=streamable_http&id=cpg-knowledge-graph-mcp&name=CPG%20Knowledge%20Graph%20%28MCP%29
It answered our last check on 18 October 2026 in 168 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
14, as returned by the server's own tools/list on 31 August 2026: check_eligibility, count_gtin_coverage, find_makers, find_retailers, get_kernel, get_signal_chain, list_brands_by_node, list_nodes, and 6 more.
It answered our last check on 18 October 2026 in 168 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.cpgknowledgegraph.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: standard-10060.org. Endpoint host: mcp.cpgknowledgegraph.ai. ARD identifier: urn:air:standard-10060.org:kg:cpg-knowledge-graph.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.