# Alpaca Guard

> Use this tool when you need to manage AI-powered trading within predefined budget constraints, preventing overspending and ensuring controlled investment strategies. Alpaca Guard solves problems of unintended excessive trading by enforcing daily USD spending limits and providing a safe environment for testing through paper mode. It accepts account and trading parameters as inputs and outputs controlled order executions and account status updates.

Canonical page: https://skillsregistry.net/skills/evidai-alpaca-guard  
JSON: https://api.skillsregistry.net/v1/skills/evidai-alpaca-guard

## Description

Alpaca Guard wraps the Alpaca Markets brokerage API with an enforced daily USD spending limit that prevents AI agents from exceeding configured budgets. Orders are preflighted against a local ledger before any Alpaca call executes, and trading defaults to paper mode until live trading is explicitly enabled. Eight tools cover account status, position management, quote lookup, and guarded order placement and closure.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/evidai-alpaca-guard)
- **Repository:** <https://github.com/evidai/agent-payment-mcp/tree/HEAD/alpaca-guard-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "evidai-alpaca-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/evidai-alpaca-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/evidai-alpaca-guard/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt