FCHubFCHub.co

Tool Reference

Every tool in FluentCart MCP, listed by module. 274 tools covering orders, products, customers, subscriptions, shipping, tax, reports, and more.

The complete inventory. Every tool, every module, every HTTP method. 274 tools organised into 27 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 274 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 274 upfront. Same tools, same results — just lazily loaded.

Categories for filtering: product, order, customer, coupon, report, subscription, integration, setting, shipping, tax, email, role, file, 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

Every tool is tagged 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)55Full catalogue management
Customers19Profiles, addresses, stats
Subscriptions7Lifecycle management
Coupons12Discounts and promotions
Reports (Core + Insights)45Analytics and metrics
Shipping15Zones, methods, classes
Tax22Rates, EU VAT, records
Email Notifications8Templates and settings
Order Bumps5Upsell offers
Product Options10Attributes and terms
Integrations12Third-party addons
Settings14Store configuration
Roles & Permissions7Access control
Labels3Order tags
Activity3Audit log
Notes1Order annotations
Dashboard2Overview stats
Application4App info
Files4File management
Public4Public-facing
Miscellaneous4Utilities
Total (static mode)274
Total (dynamic mode)3Meta-tools that proxy to all 274

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.

Response transforms and in-memory caching keep token usage tight. Static reference data is cached with TTL, and heavy list responses are trimmed before they reach the AI.

MCP Resources

Four read-only resources for reference data. These are browsable context the AI can read without calling tools — useful for grounding conversations with store configuration:

Resource URIDescription
fluentcart://store/configStore settings and configuration (currency, locale, modules)
fluentcart://store/countriesSupported countries and their details
fluentcart://store/payment-methodsConfigured payment methods
fluentcart://store/filter-optionsAvailable filter options for orders, products, customers

Resources are application-controlled — the client decides when to read them. Static data is cached in-memory, so repeated reads don't hit the API.

MCP Prompts

Five pre-built workflows that guide the AI through multi-step operations. Think of them as recipes — the AI knows which tools to call and in what order:

PromptArgumentsWhat It Does
analyze-store-performancestartDate, endDateRevenue overview, KPIs, and best sellers for a date range
investigate-orderorder_idDeep-dive into order details, transactions, and activity timeline
customer-overviewcustomer_idFull customer profile with stats, addresses, and spending history
catalog-summary(none)Catalog health report — product count, top sellers, store metrics
subscription-healthstartDate, endDateSubscription churn, renewal success, and revenue forecast

Not all MCP clients support prompts yet. Claude Desktop and Claude Code do. If yours doesn't, just ask for the same thing in plain English — the AI will figure out the same tool sequence on its own.

Response Caching

Static reference data is cached in-memory so the AI doesn't re-fetch the same 250-country list every time it needs to validate an address:

EndpointCache TTL
Countries list1 hour
Filter options10 minutes
App init (store config)10 minutes
Report metadata10 minutes

The cache lives in the server process. Restart the server to clear it. No external dependencies, no Redis, no drama.

On this page