CPG Knowledge Graph

The Model Context Protocol (MCP) server for the beauty, cosmetics and personal care sector.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Resolve Gtin: Resolve a GTIN to its procurement readiness signal. Zero-pads input to 14 digits.
  • Check Eligibility: Check whether a GTIN can ship to a specific retailer banner in a country.
  • Get Signal Chain: Return the full ACM-68000 signal chain for a GTIN (zero-pads to 14).

What data it sees

Do you need an account

No: the server works without sign-in

The Model Context Protocol (MCP) server for the beauty, cosmetics and personal care sector. Point an AI agent at it and it knows the market: 78,284 brand records, 16,378 makers and 15,529 retail banners across 50 markets, kept live. An agent learns which brands exist, who makes them, which retailers carry the category, whether a product can ship to a given banner in a given country, and gets one deterministic signal on every answer. Open for read, no account, no key. Operated by GreenCore Solutions Corp.

How to connect

How to connect CPG Knowledge Graph to Claude

The server address to paste into Claude settings:

https://cpg-knowledge-graph--greencore-solutions.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect CPG Knowledge Graph to ChatGPT

The server address to paste into ChatGPT settings:

https://cpg-knowledge-graph--greencore-solutions.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect CPG Knowledge Graph to Cursor

The server address to paste into Cursor settings:

https://cpg-knowledge-graph--greencore-solutions.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (14)

Raw names from tools/list. Only developers need these.

resolve_gtinResolve a GTIN to its procurement readiness signal. Zero-pads input to 14 digits.
check_eligibilityCheck whether a GTIN can ship to a specific retailer banner in a country.
get_signal_chainReturn the full ACM-68000 signal chain for a GTIN (zero-pads to 14).
count_gtin_coverageGlobal coverage statistics: GTINs, nodes, makers (supply), retailers (demand).
resolve_scopeGSC 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.
list_nodesThe 49 sovereign nodes (the spine) — each with its GS1 GTIN and CLEAN per-node maker (supply) and retailer (demand) counts (separate subqueries, never summed).
resolve_nodeResolve one node: its GS1 license + its makers (supply) + its retailers (demand).
find_makersGlobal cross-node maker (supply) search. Filter by segment / region / node / has_website.
find_retailersGlobal cross-node retailer (demand) search. Filter by region / node / parent_banner.
node_marketSupply↔demand bridge for ONE jurisdiction: makers (supply) and retailers (demand) as two separate counts (never summed), plus the same-node potential bridge pairs.
list_sku_typesSPARKS 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.)
list_brands_by_nodeSPARKS 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.
get_kernelSPARKS 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 — do NOT compute a score. Never returns a pack/size.
resolve_sparksTwo-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/size VALUE is NEVER returned. Route to Navigator. Brand match is fail-closed (normalized exact match); uncertainty -> recognized:false.