About PNL Toolkit
Eight free investment and trading calculators with PNG charts and editable result links
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://pnltoolkit.com/mcpclaude mcp add --transport http com-pnltoolkit-calculators https://pnltoolkit.com/mcp{"mcpServers":{"com-pnltoolkit-calculators":{"type":"http","url":"https://pnltoolkit.com/mcp"}}}Open in Cursor{"servers":{"com-pnltoolkit-calculators":{"type":"http","url":"https://pnltoolkit.com/mcp"}}}Open in VS Code{"mcpServers":{"com-pnltoolkit-calculators":{"type":"http","url":"https://pnltoolkit.com/mcp"}}}{"mcpServers":{"com-pnltoolkit-calculators":{"serverUrl":"https://pnltoolkit.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
8| Parameter | Type | Required | Description |
|---|---|---|---|
| end | string | No | End month, YYYY-MM. Must be within the installed data snapshot. |
| unit | enum | No | cash for a dollar budget; coins for a coin or share quantity.cash | coins |
| asset | enum | No | Asset ticker. Available historical start dates vary by asset.BTC | ETH | SOL | SPY | QQQ | VTI | VXUS | GLD | TLT | AAPL | MSFT | NVDA | TSLA |
| start | string | No | Start month, YYYY-MM. |
| amount | number | No | Dollar budget including fees, or coin/share quantity when unit is coins. |
| buyFee | number | No | Buying fee as a percentage, e.g. 0.1 means 0.1%. |
| benchmark | enum | No | Optional benchmark asset.none | SPY | QQQ | BTC |
| returnBasis | enum | No | total reinvests distributions; price excludes distributions.total | price |
| include_image | boolean | No | Also inline a PNG no wider than 1000 pixels. Image URL is always returned. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.