About Smolabot
Deterministic decision guardrail for AI agents and bots. Verifies pre-trade economics (long-only)
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://smolabot.arison8.com/mcpclaude mcp add --transport http com-arison8-smolabot https://smolabot.arison8.com/mcp{"mcpServers":{"com-arison8-smolabot":{"type":"http","url":"https://smolabot.arison8.com/mcp"}}}Open in Cursor{"servers":{"com-arison8-smolabot":{"type":"http","url":"https://smolabot.arison8.com/mcp"}}}Open in VS Code{"mcpServers":{"com-arison8-smolabot":{"type":"http","url":"https://smolabot.arison8.com/mcp"}}}{"mcpServers":{"com-arison8-smolabot":{"serverUrl":"https://smolabot.arison8.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.
https://smolabot.arison8.com/mcpAuth requiredTools
1| Parameter | Type | Required | Description |
|---|---|---|---|
| side | enum | Yes | Long-only: "buy". Shorts are rejected with SIDE_NOT_SUPPORTED.buy |
| size | any | Yes | Exactly one of quantity (base units) or notional (quote currency, at the entry reference price). |
| symbol | string | Yes | Label only; does not affect the math. |
| exit_price | number | Yes | Expected exit reference (mid) price, before spread, slippage and fees. |
| spread_bps | number | Yes | FULL bid/ask spread in bps; a taker leg pays half. |
| entry_price | number | Yes | Entry reference (mid) price, before spread, slippage and fees. |
| slippage_bps | number | Yes | Adverse slippage per taker leg, in bps. |
| maker_fee_bps | number | Yes | |
| taker_fee_bps | number | Yes | |
| exit_liquidity | enum | Yes | maker | taker |
| entry_liquidity | enum | Yes | maker | taker |
| profit_buffer_bps | number | No | Optional required net return in bps; omitted means 0 (echoed in assumptions). |
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.