A connection to Final POS, a system for running a shop’s sales and operations. It covers products, stock, orders, customers, reports, staff, bookings, and custom checkout apps.

It helps manage a shop’s catalogue, inventory, purchases, sales, customers, and reports, and helps build, test, and deploy POS, kiosk, or self-checkout apps.

It brings store data and checkout-app work into an agent instead of requiring separate manual systems.

final — Skill for Claude Code by Final-Commerce/final-pos-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 Final-Commerce/final-pos-mcp --skill final

Clone the repo

git clone --depth 1 https://github.com/Final-Commerce/final-pos-mcp

Made for: Claude Code.

Or install final, 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/final-commerce/final-pos-mcp/final/github.svg)](https://agentmods.dev/skills/final-commerce/final-pos-mcp/final)

Your own site

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

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,271 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	$0.00072	$0.01271
Opus 5.5	$0.00029	$0.00508
Sonnet 5.5	$0.00014	$0.00254
Haiku 4.5	$0.00007	$0.00127

Measured today against content hash a4b4f473bfec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

final 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 today.

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.

plugins/final/skills/final/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with Final

You are connected to the Final MCP server (final, https://ai.finalpos.com/mcp). Final is the commerce platform behind the merchant's point of sale. The server reaches every Final product through one connection, acting as the person who connected it, on one company, within the packs they allowed:

hub_* tools: Hub, the back office. Products, categories, modifiers, stock, suppliers and purchase orders, customers, orders, reports, team and roles, outlets, stations, taxes, media, bookings, extensions.
flow_* tools: Flow, the app builder. Custom POS, kiosk, self-checkout and payment-terminal apps, with grounding, blueprints, preview sandboxes, validation and deploys.

Start every session the same way

Call get_connection. It returns who you act as, the company Hub tools act on, the other companies you can switch to, and which packs are allowed and listed.
If no company is selected and you need Hub, call switch_company.
If the job needs tools you can't see, call find_tools with a plain description ("low stock", "purchase order", "deploy the app"). Call the match with call_tool, or enable_packs to list its whole pack. Don't tell the user a capability is missing until find_tools comes back empty.

Packs: catalog, inventory, orders, customers, reports, team, store, bookings (Hub) and build, build_data (Flow). If a tool is in a pack this connection doesn't allow, tell the user they can widen it at https://ai.finalpos.com/connections.

Rules

Confirm before changing live data. Tools with readOnlyHint: false change the merchant's real store. Say what will change and wait for a yes before deploys, deletes, price changes and bulk imports. Reads need no confirmation.
Never invent ids. Look up products, customers, outlets and flows first.
Money stays on the till. You can't take payments, refund or void orders. Orders are read-only.
Secrets never pass through you. Use flow_request_secret so the merchant enters API keys in the builder. Never write a key into a file.
Show your work in money terms. When you report sales or stock, give the period, outlet and currency you used.

Read the full file on GitHub · 98 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.

today First seen · 98 lines · 72 tokens per session scan A a4b4f473bfec

Subscribe to this mod's changes

final is a skill published in the GitHub repository Final-Commerce/final-pos-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 1,271 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 2026-10-18.

E-commerce ai-agents gemini-cli gemini-cli-extension kiosk mcp mcp-server

skills

Skill "skills" from TheBestCo/bestprice-mcp, covering bestprice, route by shopper intent, preserve evidence and price semantics, optional price-drop events and boundaries.

TheBestCo/bestprice-mcp · 0 tokens

maqami-travel-booking

Search and compare hotels and flights with the MAQAMI Travel MCP server (https://mcp.maqami.co/) and send the customer a secure checkout link on book.maqami.co. Use when the user asks to find hotels or flights for specific dates, compare rates, read hotel details or reviews, look up airports, book a hotel room or…

negm17111995/mcp-server · 92 tokens

visual-explainer-extension

Generate strikingly well-designed, visually pleasing HTML diagrams and reports. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII…

Jakedismo/visual-explainer-extension · 84 tokens

final