Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Agentic Commerce RFQ Multi-Vendor Bidding Arbiter compare these 3 supplier bids for 5,000 lenses and pick the lowest landed-cost winner"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Official Website: https://www.genpark.ai
LinkedIn: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)
Autonomous B2B RFQ (Request for Quote) Multi-Vendor Bidding Arbiter. Scores wholesale quotations across unit volume pricing, minimum order quantities (MOQ), landed tariffs, net payment terms (Net 30/60), and historical supplier lead-time reliability.
GenPark Official Website: https://www.genpark.ai
LinkedIn Official Page: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)
Related MCP server: genpark-cross-platform-commerce-inventory-arbitrage-skill
100% Zero External Dependencies: Runs entirely on the Python 3.9+ standard library.
Model Context Protocol (MCP) Standard: Native support for JSON-RPC 2.0 initialize, tools/list, and tools/call.
Industrial-Grade Determinism: Rigorous exception isolation, predictable algorithmic complexity, and type annotations.
Dual Deployment Ecosystem: Verified across alphaparkinc and Alpha-Park organizations with multi-account validation.
from client import AgenticCommerceRFQMultiVendorArbiter
def main():
arbiter = AgenticCommerceRFQMultiVendorArbiter()
rfq = {"part_number": "OPTIC-LENS-F2", "target_quantity": 5000, "max_unit_budget": 25.0}
bids = [
{"vendor_name": "Zeiss Industrial", "unit_price_usd": 22.0, "moq": 2000, "shipping_cost_usd": 800.0, "payment_terms_days": 90, "quality_rating_pct": 99.5},
{"vendor_name": "Apex Optics Co", "unit_price_usd": 19.5, "moq": 5000, "shipping_cost_usd": 1200.0, "payment_terms_days": 30, "quality_rating_pct": 94.0}
]
res = arbiter.arbitrate_vendor_bids(rfq, bids)
w = res['winning_vendor']
print("--- B2B RFQ Multi-Vendor Arbitration ---")
print(f"Selected Supplier: {w['vendor_name']} (Score: {w['arbitration_score']})")
print(f"Landed Cost: ${w['total_landed_cost_usd']} (Adjusted Net Terms: ${w['adjusted_cost_with_terms_usd']})")
if __name__ == "__main__":
main()
Start standard JSON-RPC 2.0 server over stdio:
python mcp_server.pyExecute embedded test harness:
python mcp_server.py --testInspect skill.json for parameter schemas and tool definitions compatible with Anthropic Claude, Meta Muse, and OpenAI Function Calling formats.
Licensed under the MIT License. Copyright © 2026 GenPark AI. Follow us on LinkedIn: https://www.linkedin.com/company/92955550 | https://www.llinkedin.com/company/92955550
This server cannot be deployed
Supplier sourcing, procurement, commercial intelligence, RFQ routing and B2B deal coordination.
Deep purchase intelligence for agents and apps: live prices, landed cost, trust scores. Free.
Agent-native supply network for components, fabrication, industrial RFQs, offers, and fulfillment.
A2A + MCP hub for retail grocery procurement — 20 markets on the SCHEMA algo record. Trade only.
