FCHubFCHub.co

Tool Reference

Every tool I built into FluentCart MCP, listed by module. 194 tools covering orders, products, customers, subscriptions, reports, and more.

This is the complete inventory. Every tool, every module, every HTTP method. I organised 194 tools into 17 modules so the AI (and you) can find what it needs.

You'll never need to call these yourself — the AI picks the right tool based on what you ask. But if you want to know exactly what's possible, or you want to verify that a specific capability exists before asking for it, this is your reference.

Every tool follows the naming pattern fluentcart_{resource}_{action}.

Relax

This page is a lookup table, not homework. The AI already knows all of this. You're here out of curiosity or because you want to confirm something specific.

Dynamic Mode

Don't fancy loading 194 tool definitions into your LLM context? Fair enough. Start the server with --mode dynamic and you get 3 meta-tools instead:

ToolWhat It Does
fluentcart_search_toolsSearch tools by keyword and optional category. Returns names, titles, descriptions.
fluentcart_describe_toolsGet full input schemas and annotations for specific tools (max 10 per request).
fluentcart_execute_toolExecute any tool by name with provided input.

The AI discovers tools on demand instead of loading all 194 upfront. ~96% token reduction (~20K down to ~1.5K). Same tools, same results — just lazily loaded.

Categories for filtering: product, order, customer, coupon, report, subscription, integration, setting, label, activity, note, dashboard, application, public, misc.

Trade-off

Dynamic mode adds 2-3 extra tool calls per workflow (search, describe, then execute). If latency matters more than token budget, stick with the default static mode.

Tool Annotations

I tag every tool with metadata so the AI knows what it's dealing with:

AnnotationWhat It Means
Read-onlyOnly reads data. Can't break anything. Call it all day.
IdempotentSame call, same result. Safe to retry if something times out.
DestructiveDeletes data permanently. The AI should (and usually does) confirm first.
Open-worldCreates new data — orders, products, customers.

The Numbers

ModuleToolsType
Orders (Core + Transactions)23CRUD + workflows
Products (Core + Pricing + Variants + Catalogue)53Full catalogue management
Customers17Profiles, addresses, stats
Subscriptions7Lifecycle management
Coupons11Discounts and promotions
Reports (Core + Insights)27Analytics and metrics
Order Bumps5Upsell offers
Product Options10Attributes and terms
Integrations12Third-party addons
Settings8Store configuration
Labels3Order tags
Activity3Audit log
Notes1Order annotations
Dashboard2Overview stats
Application4App info
Public4Public-facing
Miscellaneous4Utilities
Total (static mode)194
Total (dynamic mode)3Meta-tools that proxy to all 194

Key endpoints also feature response transformsorder_get, product_get, customer_get and all list endpoints strip HTML blobs, embedded objects, and serialised metadata before returning. Less noise, fewer tokens, same useful data.

Static reference data (countries, filter_options, app_init, report_meta) is cached in-memory with TTL, so repeated calls don't hit the API again.

And there's about 130 more coming in v1.1 — shipping, taxes, email templates, customer portal, checkout, and the niche analytics nobody asked for but I built anyway.

On this page