Skip to main content
Glama
FLUF-io

@fluf/mcp

Official
by FLUF-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

list_products

List an authenticated seller's FLUF products with vid, title, price, stock, source, and live channels. Filter by liveness=confirmed for accurate live catalogue counts.

Instructions

List the authenticated seller's FLUF products. Each row carries a vid — the product handle the crosslist tool takes — plus title, price, stock, source channel and the channels it is already live on.

IMPORTANT for audits and counts: status is what the channel last told FLUF, not a live check, so an ended listing keeps reading 'active'. Each row also carries liveness ('confirmed' | 'unconfirmed' | 'unknown'), last_seen_at and last_seen_age_hours — when a channel scan last returned that listing. When counting a seller's live catalogue, or deciding whether two rows are duplicates, pass liveness: "confirmed" and say so. Do not filter the rows yourself and quote total — total counts everything the filter did not exclude, so an unfiltered call reports the seller's whole index history as if it were live. Two 'active' rows for the same item are usually one listing that ended and its relist, not a duplicate — channels mint a new listing id on relist. Never advise ending a listing on the strength of this tool alone; tell the seller to confirm on the channel first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo1-indexed page. Default 1.
searchNoSearch by title or SKU.
sourceNoFilter by the channel a product came FROM (e.g. 'shopify', 'depop'). Call list_channels for the values valid on this account. Omit for all sources.
statusNoListing status. Omit to get in-stock products only (a `search` with no status covers sold ones too). 'sold' = products FLUF holds as out of stock, i.e. sold on some channel; 'all' = in and out of stock. Note that `status` is FLUF's record of what the channel last said, so a listing that has since ended still reads 'active'. Use each row's `liveness` field to tell live from stale.
livenessNoFilter by whether the channel has recently confirmed the listing still exists. Use 'confirmed' whenever you are COUNTING a seller's live catalogue or deciding whether two rows are duplicates — it narrows `total` as well as the rows, which `status` does not.
per_pageNoResults per page. Default 20, max 100.
crosslisted_toNoOnly products already live on these channels.
not_on_platformsNoOnly products NOT yet on these channels — the usual way to find crosslist candidates.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.7
    • addedInput schema / properties / liveness
      Added value: +{
+  "description": "Filter by whether the channel has recently confirmed the listing still exists. Use 'confirmed' whenever you are COUNTING a seller's live catalogue or deciding whether two rows are duplicates — it narrows `total` as well as the rows, which `status` does not.",
+  "enum": [
+    "confirmed",
+    "unconfirmed",
+    "unknown"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / status / description
      Previous value: -"Listing status. Default: active."New value: +"Listing status. Omit to get in-stock products only (a `search` with no status covers sold ones too). 'sold' = products FLUF holds as out of stock, i.e. sold on some channel; 'all' = in and out of stock. Note that `status` is FLUF's record of what the channel last said, so a listing that has since ended still reads 'active'. Use each row's `liveness` field to tell live from stale."
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and delivers: `status` is a stale channel record, not a live check; `total` counts everything the filter did not exclude; relists mint new listing ids so two 'active' rows are usually not duplicates. It also surfaces the downstream risk (never advise ending a listing from this tool alone).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and the caveats are dense but each earns its place (staleness, counting, duplicates, safety). It is longer than typical and the bolded middle block leans heavy, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by naming the fields returned (vid, liveness, last_seen_at, last_seen_age_hours) and their semantics. For an 8-param read tool with no annotations, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema alone leaves implicit: that `liveness` narrows `total` while `status` does not, and that omitting status yields in-stock plus, via search, sold items. That interplay is genuinely useful beyond the per-field text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the authenticated seller's FLUF products') plus scope, and immediately enumerates the row payload (vid, title, price, stock, source channel, live channels). This clearly separates it from siblings like list_drafts and list_channels.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent when to use `liveness: "confirmed"` (counting a live catalogue, judging duplicates), warns against filtering rows manually and quoting `total`, and states the tool must not be used alone to justify ending a listing. Alternatives and exclusions are all named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools