# Pancake — Verifiable Backtests for AI Agents

> Use this tool when you need to verify the performance of AI-built trading strategies through reproducible and deterministic backtests, solving problems of reliability and trust in AI-driven trading decisions. It takes in AI trading strategies as input and outputs verifiable, reproducible results. Use Pancake in contexts where trustworthy and transparent trading strategy evaluation is crucial.

Canonical page: https://skillsregistry.net/skills/com-usepancake-pancake-mcp  
JSON: https://api.skillsregistry.net/v1/skills/com-usepancake-pancake-mcp

## Description

Verifiable backtests for AI-built trading strategies: deterministic engine, reproducible results.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-09-03

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.usepancake%2Fpancake-mcp)

## Use it

MCP endpoint published by the skill: `https://mcp.usepancake.com/api/mcp`

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": "com-usepancake-pancake-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-usepancake-pancake-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-usepancake-pancake-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