Discovery is public, execution is authorized
The tool discovery endpoint is public for planning, while execution still requires the matching assistant authorization and workspace controls.
Developer platform
AI agents and MCP tools for merchandise automation
Connect AI assistants to approved MerchandAise capabilities through MCP-compatible tool discovery, authorization boundaries, and production review paths for safe merchandise automation.
What this page covers
This is the dedicated discovery page for AI agent builders evaluating MerchandAise MCP-compatible tool access. It explains the public discovery endpoint, the assistant authorization boundary, and the launch review path.
Use it when an assistant needs structured access to merchandise discovery, quoting, or approved operations without bypassing human governance.
AI agent and MCP surfaces
| Surface | Human guide | Machine contract | Access |
|---|---|---|---|
| MCP toolsExpose approved MerchandAise capabilities to AI agents through discoverable MCP-compatible tool definitions and execution endpoints with assistant authorization. | View MCP server card | Open MCP tools endpoint/api/v1/mcp/tools | public Public tool discovery endpoint; tool execution still requires the matching assistant authorization. |
| API docsReview human-readable docs and machine-readable OpenAPI contracts for planning, testing, and versioned release management. | Explore API and integrations | OpenAPI JSON/api/docs/openapi.json | public Public machine-readable OpenAPI JSON for client generation and contract review. |
Production implementation checklist
- 01
Start with public tool discovery
Use the MCP tools discovery JSON to understand available tool definitions, expected inputs, and the difference between discovery and execution.
- 02
Design assistant authorization deliberately
Map which assistant actions can be read-only, which need user confirmation, and which require workspace or enterprise approval before execution.
- 03
Test agent behavior before launch
Validate prompts, tool calls, failure states, observability, and approval handoffs in staging before enabling live merchandise workflows.
Production safeguards
Human review for sensitive operations
Quoting, ordering, supplier, and enterprise actions should keep approval checkpoints instead of relying only on autonomous tool calls.
LLM-friendly source of truth
The page has canonical metadata, structured data, a dedicated LLM feed, and stable links so assistants can cite the current integration surface.
FAQ
What is the MerchandAise MCP tools endpoint for?
It lets builders discover MCP-compatible tool definitions for approved MerchandAise capabilities. Discovery is public, while execution still requires authorization.
Can an AI agent place orders automatically?
Production agent workflows should preserve the required approval, authentication, and workspace controls before any sensitive operation is executed.
Is there a dedicated LLM feed for this page?
Yes. The page exposes a focused LLM feed at /llm/developers/ai-agents-mcp with the canonical summary, tool links, safeguards, and implementation checklist.
Planning an agent workflow?
Share the assistant use case, target users, approval model, and required tools. We will recommend the right MCP, API, and governance pattern.