# run_backtest

Run a backtest on historical data for a trading strategy via the GT backtest service.

Agent View of the PolicyLayer registry record for `run_backtest`. HTML page: https://policylayer.com/tools/gt-protocol-mcp/run-backtest

## Facts

- Tool: `run_backtest`
- Server: :GT Protocol MCP Server (`gt-protocol/mcp`) — https://policylayer.com/tools/gt-protocol-mcp.md
- Homepage: https://github.com/gt-protocol/mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run_backtest",
    "arguments": {}
  }
}
```

## Why run_backtest is rated High

While backtesting operates on historical data rather than live markets, it is fundamentally an Execute operation: it runs strategy code through the GT backtest service. The severity is high because misconfigured or malicious strategies could consume excessive resources, reveal sensitive trading logic, or be used to probe exchange APIs.

From the tool's own definition: "The tool 'run_backtest' executes a trading strategy against historical data via the GT backtest service. The description indicates it 'runs' a backtest, which involves executing code/logic."

## Use case

AI agents invoke run_backtest to trigger actions in :GT Protocol MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches :GT Protocol MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_backtest": {
      "limits": [
        {
          "counter": "run_backtest_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on :GT Protocol MCP Server (18)

- `delete_bot` — Destructive — https://policylayer.com/tools/gt-protocol-mcp/delete-bot.md
- `start_bot` — Execute — https://policylayer.com/tools/gt-protocol-mcp/start-bot.md
- `stop_bot` — Execute — https://policylayer.com/tools/gt-protocol-mcp/stop-bot.md
- `close_deal` — Financial — https://policylayer.com/tools/gt-protocol-mcp/close-deal.md
- `start_deal` — Financial — https://policylayer.com/tools/gt-protocol-mcp/start-deal.md
- `authenticate` — Read — https://policylayer.com/tools/gt-protocol-mcp/authenticate.md
- `get_active_deals` — Read — https://policylayer.com/tools/gt-protocol-mcp/get-active-deals.md
- `get_balance` — Read — https://policylayer.com/tools/gt-protocol-mcp/get-balance.md
- `get_bot` — Read — https://policylayer.com/tools/gt-protocol-mcp/get-bot.md
- `get_deal_history` — Read — https://policylayer.com/tools/gt-protocol-mcp/get-deal-history.md
- `get_exchanges` — Read — https://policylayer.com/tools/gt-protocol-mcp/get-exchanges.md
- `get_profile` — Read — https://policylayer.com/tools/gt-protocol-mcp/get-profile.md
- `list_bots` — Read — https://policylayer.com/tools/gt-protocol-mcp/list-bots.md
- `list_deals` — Read — https://policylayer.com/tools/gt-protocol-mcp/list-deals.md
- `list_portfolios` — Read — https://policylayer.com/tools/gt-protocol-mcp/list-portfolios.md
- `create_bot` — Write — https://policylayer.com/tools/gt-protocol-mcp/create-bot.md
- `paper_clone` — Write — https://policylayer.com/tools/gt-protocol-mcp/paper-clone.md
- `update_bot` — Write — https://policylayer.com/tools/gt-protocol-mcp/update-bot.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=gt-protocol-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/gt-protocol-mcp