How does this MCP handle rounding errors?

It uses a Penny Reconciliation Algorithm that automatically adjusts individual totals so they always sum to the exact grand total of the receipt.

Can I split items between multiple people?

Yes. You can map a single item to multiple consumers, and the engine will split that item's cost before calculating taxes and tips.

Does this work with any AI client?

It works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Is the math actually accurate?

Yes. It offloads the math from the LLM to a dedicated V8 mathematical engine to prevent the hallucinations common in standard AI models.

How are taxes and tips distributed?

The engine calculates a proportional burden, meaning each person pays a share of the tax and tip based on their specific subtotal.

How does it handle shared items like an appetizer?

The agent passes an array of 'consumers' for each item. If 'Nachos' ($15) has consumers ['John', 'Jane'], the engine automatically divides the base cost ($7.50 each) before proportionally applying their individual tax and tip burden.

Why do LLMs fail at this without an MCP?

LLMs lack true mathematical persistence. When calculating multi-step proportions (subtotal -> ratio -> tax allocation -> tip allocation -> fractional rounding), they often lose tracking of pennies, resulting in individual totals that don't add up to the receipt's grand total.

What is the 'Penny Reconciliation Algorithm'?

Due to floating-point toFixed(2) rounding on 5 different people, the sum of individual owed amounts might equal $100.01 while the actual grand total is $100.00. The engine detects this and surgically subtracts or adds the penny discrepancy to guarantee an exact match.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Deterministic Fair-Share Tip Splitter to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get mathematically perfect bill splits without rounding errors.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 1 capability

We ship only the actions that matter.

Capability set01 / 01

01

1 capability in this set.

Part of 1 available through Deterministic Fair-Share Tip Splitter.

01
Split bill
This capability calculates individual shares by distributing taxes and tips proportionally based on specific items consumed. It uses a built-in algorithm to resolve any rounding discrepancies so the math always balances.

Real work

What teams actually run

Group Dining

Split a restaurant bill where some people shared appetizers and others had individual entrees.

Expense Management

Calculate exact tax and tip distributions for business meal reimbursements.

Shared Household Bills

Distribute utility or grocery costs proportionally among roommates based on usage.

Event Budgeting

Split large vendor invoices among multiple stakeholders with precise tax allocations.

Automate a task

Put Deterministic Fair-Share Tip Splitter to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Deterministic Fair-Share Tip Splitter works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Deterministic Fair-Share Tip Splitter to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

888ms average. Fast in production.

Deterministic Fair-Share Tip Splitter is checked daily against the live service.

Daily averagePeak 1090ms

Oct 3Today

Fastest day: 696ms
Slowest day: 1090ms
14-day trend: Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 1 capability arrives ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Deterministic Fair-Share Tip Splitter, so you can see the experience inside your AI.

It does not authenticate your account with Deterministic Fair-Share Tip Splitter. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Deterministic Fair-Share Tip Splitter Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_8HLUdnAaXQJO4EgNA42edHGNO0scKItSo0N7Ebqj/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Deterministic Fair-Share Tip Splitter capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "deterministic-fair-share-tip-splitter-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_8HLUdnAaXQJO4EgNA42edHGNO0scKItSo0N7Ebqj/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Deterministic Fair-Share Tip Splitter in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Deterministic Fair-Share Tip Splitter owners hand off.

This MCP is for anyone using AI agents to manage group finances or detailed ledgers where math accuracy is non-negotiable.

01
Personal Assistants
Hand off complex group dinner math to the agent to ensure everyone is charged correctly.
02
Accountants
Use the agent to process itemized receipts with perfect mathematical closure.
03
Event Coordinators
Delegate the calculation of shared costs and proportional fees for group events.

FAQ

Questions Deterministic Fair-Share Tip Splitter owners ask.

01
How does this MCP handle rounding errors?
It uses a Penny Reconciliation Algorithm that automatically adjusts individual totals so they always sum to the exact grand total of the receipt.
02
Can I split items between multiple people?
Yes. You can map a single item to multiple consumers, and the engine will split that item's cost before calculating taxes and tips.
03
Does this work with any AI client?
It works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
04
Is the math actually accurate?
Yes. It offloads the math from the LLM to a dedicated V8 mathematical engine to prevent the hallucinations common in standard AI models.
05
How are taxes and tips distributed?
The engine calculates a proportional burden, meaning each person pays a share of the tax and tip based on their specific subtotal.
06
How does it handle shared items like an appetizer?
The agent passes an array of 'consumers' for each item. If 'Nachos' ($15) has consumers ['John', 'Jane'], the engine automatically divides the base cost ($7.50 each) before proportionally applying their individual tax and tip burden.
07
Why do LLMs fail at this without an MCP?
LLMs lack true mathematical persistence. When calculating multi-step proportions (subtotal -> ratio -> tax allocation -> tip allocation -> fractional rounding), they often lose tracking of pennies, resulting in individual totals that don't add up to the receipt's grand total.
08
What is the 'Penny Reconciliation Algorithm'?
Due to floating-point toFixed(2) rounding on 5 different people, the sum of individual owed amounts might equal $100.01 while the actual grand total is $100.00. The engine detects this and surgically subtracts or adds the penny discrepancy to guarantee an exact match.

Explore

More in Productivity

Connect Deterministic Fair-Share Tip Splitter to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01

Split bill

What teams actually run

Group Dining

Expense Management

Shared Household Bills

Event Budgeting

Building your own app? The connector is yours to use.

Deterministic Fair-Share Tip Splitter Connector

Claude Desktop

Personal Assistants

Accountants

Event Coordinators

How does this MCP handle rounding errors?

Can I split items between multiple people?

Does this work with any AI client?

Is the math actually accurate?

How are taxes and tips distributed?

How does it handle shared items like an appetizer?

Why do LLMs fail at this without an MCP?

What is the 'Penny Reconciliation Algorithm'?

Currency Math Engine AI Connector

Financial Math Engine AI Connector

TaxJar AI Connector

Percentage Calculation Engine AI Connector

Suggestions

R&D Tax Credit Calculator AI Connector

Tip & Tax Splitter AI Connector

Tax Loss Harvesting Calculator AI Connector

Tip Split Trick Calculator AI Connector