eCommerce

a2a-grocery.ai

MCP server for resolving market jurisdiction and actor, gating transactions, and querying market-cleared product SKU records with detailed attributes like temperature, allergens, and offers.

2 endpoints19 known toolsFirst detected October 3, 2026Last detected October 3, 2026

ENDPOINT 1

https://mcp.a2a-grocery.ai/mcp

No auth detected

MCP server metadata

Name: a2a-grocery
Version: 1.0.0

Capabilities

loggingprompts.listChangedresources.listChangedtools.listChanged

Server instructions

Agent-to-Agent (A2A) + Model Context Protocol (MCP) hub for retail grocery. Business to business: makers, brand owners, private label, distributors, importers, retailers and their AI agents (GreenCore Solutions Corp.). Call resolve_jurisdiction, then resolve_actor, then gate_transaction before any availability, price, documents, order or handoff tool; those tools refuse without an allow decision. Twenty markets on the SCHEMA algo grocery record; ambient, chilled, frozen and fresh; organic, free-from, plant-based, artisan, origin and premium lanes. Every record field carries its source page; every response carries notice; every record carries claim_status (listed · claimed · verified). Artificial intelligence makes mistakes. A2A Grocery is an agentic information source, not a recommendation. No ads, ever. No rank for sale. Trade only.

Known tools 19

resolve_jurisdiction

Where is this going?

Inferred read-only

resolve_actor

Who is asking?

Inferred read-only

gate_transaction

Allow or deny, with the reason and the rule.

Inferred read-only

search_cleared_items

Find items cleared for this market: validated SKU records in a market (query by product name, brand, maker or category; filters: temperature ambient · chilled · frozen · fresh, attribute lane organic · free-from · plant-based · artisan · origin · premium, department).

Inferred read-only

get_item

One item by GTIN (EAN in European copy), fully resolved: temperature, department → super category → category, attribute lanes, pack, brand and maker, market, claim status, market status, availability; after the gate also ingredients, allergens, claims, origin, certificates, variants and offers.

Inferred read-only

verify_gtin

Is this GTIN real, and whose is it?

Inferred read-only

get_label_and_claims

What the label must say, and which claims are allowed: the labelling requirements of the market (food information, allergens, origin, nutrition) and the claims rules of record (nutrition and health claims, organic, free-from), each with its source page.

Inferred read-only

compare_items

Compare items, variants and pack sizes side by side (two to eight GTINs or catalogue ids).

Inferred read-only

find_verified_buyer

Retail buyer desks for this market: banner records (banner, parent group, channel discounter · e-commerce · local · in-store · traditional, local format, cited POS count or NULL, buyer desk by department) with their claim status — verified first, then claimed, then listed.

Inferred read-only

find_verified_supplier

Verified makers, brand owners, private-label owners, distributors and importers for this item or category in a market: maker records with their claim status — verified first, then claimed, then listed.

Inferred read-only

get_product_documents

Certificates and paper: the documents on an item record (organic certificate, PDO/PGI, halal, kosher, specification, allergen statement, origin declaration, lot where it applies), each a URL with its read date and source class; decision_id required.

Inferred read-only

log_audit

Write a line to the audit record for a gate decision, an order intent or a handoff (returns the line id).

Potential side effects

get_price

The price for this buyer: the price basis (list · contract · promotion window) from the maker's offers on the record, once gate_transaction has answered allow (decision_id).

Inferred read-only

get_availability

In stock, and where: the availability block of an item (banners on the shelf of record, product URLs read live at load, POS counts where the banner record carries a cited one) once gate_transaction has answered allow (decision_id).

Inferred read-only

create_order_intent

Open an order between two agents: an order intent for a cleared item after the gate; the intent carries reason_code + rule_set_version and settles by x402 on a2a-x402.

Inferred read-only

a2a_handoff

Hand the buyer to the right agent over Agent-to-Agent (A2A): with an allow decision the order intent goes to the counterparty's agent (envelope + card URL); with a deny, the market agent of the ship-to — a referral, never a sale to a consumer.

Inferred read-only

get_market_status

Is this product type a food here, and under which regime?

Inferred read-only

get_notification_requirements

What must be filed before sale in a market: the food business registration or import notification scheme, the food business operator of record, and, for a product type in a special class, the extra step (novel-food authorisation, organic certification, supplement notification) — each with its source page.

Inferred read-only

get_enforcement_watch

Recalls, withdrawals and food-safety alerts, dated: enforcement events by market, category, brand or since a date, each with its source page.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.a2a-grocery]
url = "https://mcp.a2a-grocery.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "a2a-grocery": {
      "type": "http",
      "url": "https://mcp.a2a-grocery.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: a2a-grocery
Remote MCP URL: https://mcp.a2a-grocery.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "a2a-grocery": {
      "url": "https://mcp.a2a-grocery.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "a2a-grocery": {
      "type": "http",
      "url": "https://mcp.a2a-grocery.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "a2a-grocery",
  "transport": "streamable-http",
  "url": "https://mcp.a2a-grocery.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://mcp.cpgknowledgegraph.ai/mcp

No auth detected

Known tools 0

No tool metadata was available in the registry cache.

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.a2a-grocery-ai]
url = "https://mcp.cpgknowledgegraph.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "a2a-grocery-ai": {
      "type": "http",
      "url": "https://mcp.cpgknowledgegraph.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: a2a-grocery-ai
Remote MCP URL: https://mcp.cpgknowledgegraph.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "a2a-grocery-ai": {
      "url": "https://mcp.cpgknowledgegraph.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "a2a-grocery-ai": {
      "type": "http",
      "url": "https://mcp.cpgknowledgegraph.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "a2a-grocery-ai",
  "transport": "streamable-http",
  "url": "https://mcp.cpgknowledgegraph.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for a2a-grocery.ai was fetched 2026-10-06T09:14:05.514Z.

Trust status Neutral

a2a-grocery.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.