AI commerce control plane — one MCP connection, every merchant, full checkout.
The ComOS Federation Gateway gives AI agents complete programmatic control of a live multi-merchant commerce network through a single MCP connection. Connect once and your agent can browse catalogs, manage carts, complete checkouts with Stripe payments, track orders, handle returns, and manage inventory across every merchant on the ComOS network. 39 MCP tools including 30 dedicated commerce operations plus a pass-through to the full REST API (43 endpoints). Production-validated with 5 active tenants, OAuth 2.1 with PKCE, sub-100ms agent execution, and per-tenant circuit breakers. Built for agent developers who need real commerce capabilities — not mock data, not sandboxes, live merchants with live inventory and live payments.
This is a well-documented MCP client that connects to an external ComOS Federation Gateway for e-commerce operations. The code follows good practices with proper error handling and no authentication vulnerabilities. All network calls are made to the documented external service endpoint, which is appropriate for this type of business tool. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity).
7 files analyzed · 5 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
Once installed, try these example prompts and explore these capabilities:
Be the first to review this server!
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption