A set of instructions for using MCP tools to work with a Gadget app, a web application with a GraphQL data API. It covers discovering the app's data structure, reading records, exporting data, checking logs, and making controlled changes.

Use it to inspect schemas, query or count records, group data, export CSV or JSON files, read error logs, and update or delete records when those tools are enabled.

It gives the coding agent a consistent way to find records, answer data questions, investigate errors, and avoid unsafe queries or edits.

gadget — Skill for Claude Code by Stronger-eCommerce/gadget-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Stronger-eCommerce/gadget-mcp --skill gadget

Clone the repo

git clone --depth 1 https://github.com/Stronger-eCommerce/gadget-mcp

Made for: Claude Code.

Or install gadget-mcp, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stronger-ecommerce/gadget-mcp/gadget/github.svg)](https://agentmods.dev/skills/stronger-ecommerce/gadget-mcp/gadget)

Your own site

<a href="https://agentmods.dev/skills/stronger-ecommerce/gadget-mcp/gadget"><img src="https://agentmods.dev/badge/skills/stronger-ecommerce/gadget-mcp/gadget/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/stronger-ecommerce/gadget-mcp/gadget"><img src="https://agentmods.dev/badge/skills/stronger-ecommerce/gadget-mcp/gadget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 634 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.00634
Opus 5.5	$0.00030	$0.00254
Sonnet 5.5	$0.00015	$0.00127
Haiku 4.5	$0.00008	$0.00063

Measured 6d ago against content hash 7262c506dc26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gadget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/gadget/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with a Gadget app

The gadget MCP server talks to one Gadget app's GraphQL API. Model names are singular camelCase (shopifyOrder, label).

Finding your way around

Unsure what exists? get_schema_overview (everything at once) or list_models → introspect_model.
Filters: call introspect_filters before writing a non-trivial filter. Shapes look like { financialStatus: { equals: "paid" } }, { createdAt: { greaterThan: "2026-01-01T00:00:00Z" } }, { email: { isSet: false } }. A list of filters means AND.

Reading data

query_records returns all scalar fields by default; add relations with "* customer { email }". Max 50 per page; follow endCursor with after.
"How many…?" → count_records. "…by status/vendor/etc.?" → group_count (exact for enums/booleans).
More than a page of records, or the user wants a file → export_records (CSV/JSON) and tell them the path.
run_graphql for nested/custom queries query_records can't express (read-only).

Debugging

read_logs with level: "error", a since window and search set to a record ID or action name. If it says ggt isn't logged in, ask the user to run npx ggt login once.
Prompts debug_record, audit_errors, data_health and explore_app are ready-made workflows.

Changing data (only if write tools are listed)

Look first: fetch the record(s) you'll change.
Preview: run the write with dry_run: true and show the user what will happen (for bulk_update, the match count).
Ask before applying anything that touches more than one record, deletes, or runs an action with side effects.
Apply, then re-read to confirm.

Writes run the app's real actions (validations and side effects included). GADGET_WRITE_MODELS may restrict which models can change; the tool descriptions say which.

Privacy

Fields shown as [REDACTED] are hidden on purpose by the server's settings. Don't try to work around it (aliases are refused). You can still filter by those fields.

Read the full file on GitHub · 37 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 37 lines · 76 tokens per session scan A 7262c506dc26

Subscribe to this mod's changes

gadget is a skill published in the GitHub repository Stronger-eCommerce/gadget-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 634 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.

Databases Debugging

reproduce-bug

Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…

googleapis/mcp-toolbox · 130 tokens

triage-issues

Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…

googleapis/mcp-toolbox · 164 tokens

postgresql-indexing

PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…

prowler-cloud/prowler · 108 tokens

gadget