Urgent.News

What's breaking now, across thousands of outlets.

AI

How Does the BigCommerce Store Management MCP Server Work? 16 Tools, 0 Decision Scores — Refund Held 0.50, Search 0.9545

BigCommerce's Store Management MCP server is in early access for all stores: an AI agent (Claude, ChatGPT, Cursor, Grok) can work directly with a store's catalog, pricing, inventory, orders, promotions and profile. Counted from BigCommerce's own documentation (read November 20, 2026): 16 tools — 6 reads, 9 mutating writes, and 1 refund quote that moves no money. Two writes are staged (products…

The BigCommerce Store Management MCP server, currently in early access for all stores, allows an AI agent to interact directly with various aspects of a store, including catalog, pricing, inventory, orders, promotions, and profile. The system consists of 16 tools, divided into six read functions, nine mutating write functions, and one refund quote that does not move actual money.

Two of the writes are staged, meaning they create products or promotions without actually making them visible or active. The remaining 13 functions are not staged and can significantly impact the store's functionality.

The server's decision-making process includes two named guards: an area scope (None / read-only / modify) granted per user, and per-action decision scores. These scores were tested using ScriptMasterLabs' live decision harness on November 20, 2026, with the results showing that the catalog search auto-acted at 0.9545 (bounded scope) and 0.8333 (sentence form).

Refunds, however, held at a score of 0.50, indicating a cautious approach. The system's grading layer, the ScriptMasterLabs Verdict Protocol, charges $0.005 USDC per decision and $0.005 per seal on Base via x402, verified on November 20, 2026. The full measurement, comparison table, and SELF-PROOF settlement record can be accessed at https://scriptmasterlabs.com/bigcommerce-mcp-server and https://scriptmasterlabs.com/sml-products.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

One sentence in CLAUDE.md did most of what an ADR search skill did, and karasu mapped itself (karasu weekly)

karasu is a text modeling language for system architecture, inspired by the C4 model. You describe your system in .krs files and karasu draws the views: system, deployment, and team structure.

  • Karasu text modeling language generates system, deployment, and team structure views from .krs files
  • 61 pull requests merged, including 14 Dependabot contributions and 7 ADRs
  • Six ADRs submitted in separate PRs, one ADR part of process rule alteration

New in AWS Quick: More capable flows, an updated web experience, and agents that work together

AWS Quick is the AI workspace built only for work. Today we're releasing updates that help your team get more done: build and run business-process flows in chat, triage your day in the updated web…

  • AWS Quick adds deterministic steps for consistent workflows
  • Supports multi-agent orchestration for simultaneous request handling
  • Enhanced web app with home screen, seamless tab closure experience

More from Saturday 21 November →