Skip to main content
Glama
nwjnjjj
by nwjnjjj

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
STG_LICENSE_KEYYesYour SmartTokenGuard license key (API key) from your Polar receipt.

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
stg_pricingC

Plans, prices and checkout links for SmartTokenGuard. No license needed.

stg_accountA

Check the configured license: who it is licensed to, checks used and checks remaining.

stg_inspect_renderA

Measure a rendered image or video (local path, max 32 MB / 60 s / 1080p): blur, exposure, black and frozen frames, flicker, hard cuts, impacts and flashes, and colour/lighting drift against reference_image. Uses 1 check. Returns a JSON report plus review frames — look at them for anatomy/identity defects, then call stg_qa_gate.

stg_detect_eventsC

Frames and times of impacts, flashes and cuts in a video — for placing sound effects in an editor. Uses 1 check.

stg_qa_gateB

Decide what to do with a render: PASS / NEEDS_VISUAL_REVIEW / RETRY_SAME_MODEL / SWITCH_TO_FALLBACK / HALT / HALT_BUDGET, with concrete fixes (negative-prompt terms, lower motion, new seed). technical_issues: the issues array from stg_inspect_render. semantic_defects: what you saw in the review frames ("other" + notes if unlisted). Records the attempt and its cost in a local project ledger. Free (needs a license, uses no checks).

stg_spend_reportC

What a project spent on renders, attempts per shot, first-try pass rate and failed renders caught. Local only.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 6 tools

Disambiguation4/5

Tools are mostly distinct by lifecycle stage: stg_account and stg_pricing cover license/commercials, stg_spend_report covers spend, stg_inspect_render measures technical quality, stg_detect_events finds edit points, and stg_qa_gate makes the final decision. stg_inspect_render and stg_detect_events both analyze video frames, but their outputs and stated uses differ clearly enough.

Naming Consistency4/5

All tools use the same stg_ prefix and snake_case casing, so the naming is predictable. Names mix verb_noun (stg_inspect_render, stg_detect_events) with noun_phrase labels (stg_account, stg_pricing), but that is a minor deviation rather than an inconsistent convention.

Tool Count5/5

Six tools are well-scoped for a render QA/guarding workflow, with each tool covering a distinct stage: account, pricing, spend, technical inspection, event detection, and final gate. The count is neither thin nor bloated.

Completeness4/5

The surface covers license status, pricing, spend tracking, technical render inspection, event detection, and a QA decision gate, which is a coherent lifecycle. Minor gaps remain around license activation/configuration and any explicit semantic-defect helper, but agents can work around these by supplying license state and semantic notes themselves.

Maintenance

ActivityMaintained
ResponsivenessNo issues