# pineforge-backtest-mcp

> pineforge-backtest-mcp — pineforge-4pass-pineforge-backtest-mcp. Use this tool when you need to run deterministic and accurate backtests of PineScript strategies offline, solving the problem of relying on online APIs or compromised data privacy. It takes PineScript v6 code as input and outputs verified trade results, with a proven track record of parity with TradingView. Use it when developing and testing trading strategies locally, with the convenience of a single Docker container and no required API key.

Canonical page: https://skillsregistry.net/skills/pineforge-4pass-pineforge-backtest-mcp  
JSON: https://api.skillsregistry.net/v1/skills/pineforge-4pass-pineforge-backtest-mcp

## Description

Offline MCP server: an AI agent transpiles PineScript v6 → C++ and runs deterministic, TradingView-parity backtests locally — 309/311 strict on the open corpus, 396/396 on a closed 415-script community test, ~950k trades verified, 0 engine bugs. One Docker container, no API key; code & data stay on your machine.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/pineforge-4pass/pineforge-backtest-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": "pineforge-4pass-pineforge-backtest-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pineforge-4pass-pineforge-backtest-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pineforge-4pass-pineforge-backtest-mcp/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