ListGuard
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_listingA | Audit a cross-border e-commerce product listing for compliance violations BEFORE it gets flagged or removed by the platform. Detects banned words, promo words, absolute claims (cure/heals/100%), unsupported certification claims (FDA/CE/organic), trademark risks, and missing AI content disclosure. Uses deterministic versioned rule packs — not an LLM — so every finding carries a rule id and rationale and is fully reproducible. Matching is three-level (fullwidth fold / obfuscation condense / regex with word boundaries), so "F-R-E-E shipping", "ＦＲＥＥ", and "全 场 最 低 价" are still caught while "secure" is not falsely flagged as "cure". |
| list_rule_packsA | List the available compliance rule packs with their platform, market, version, update date and rule count. Use this to discover which platforms are supported before calling audit_listing. |
| search_rulesA | Search inside a rule pack by keyword. Returns matching rules with id, severity, category, patterns, rationale and fix suggestion. Useful to answer "why was this flagged?" or "what words are banned for supplements on Temu?". |
| suggest_rewriteA | Turn audit findings into concrete rewrite guidance. For each finding it returns the offending fragment, why it violates platform policy, and the suggested replacement — grouped by field so the caller can patch the listing copy directly. Deterministic suggestions only (from the rule pack); this tool never invents copy. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: audit_listing runs the compliance check, list_rule_packs discovers packs, search_rules queries inside a pack, and suggest_rewrite produces fix guidance. The workflow ordering (discover → search → audit → rewrite) is intuitive and leaves no real risk of misselection.
All four tools follow a consistent verb_noun snake_case pattern (audit_listing, list_rule_packs, search_rules, suggest_rewrite). Verb choice is predictable and the object is always clear.
Four tools is on the lean side but appropriate for a tightly scoped compliance-auditing server; each tool earns its place in the discover/audit/rewrite loop. It is not thin enough to feel incomplete for this narrow domain.
The surface covers the full pre-flagging workflow: discovering rule packs, querying rules, auditing a listing, and generating deterministic rewrites. Minor gaps exist (e.g. no batch/multi-listing audit or report export), but core lifecycle coverage is solid.