Enterprise DNA
M MCP Servers Developer low

dolphinquant/echolon

by Various

LLM-agent-native backtest framework for futures research — MCP server, in-package skills, catalogued error codes, typed Pydantic configs. Production engine inside Qorka @ DolphinQu

D

MCP

dolphinquant/echolon

Added 1 June 2026

#agent-tools #algorithmic-trading #backtesting #claude #futures #llm-agents #mcp #mcp-server

Overview

Echolon is an LLM-agent-native backtest framework for futures research. It provides an MCP server, in-package skills, catalogued error codes, and typed Pydantic configurations. It serves as the production engine inside Qorka at DolphinQuant.

Best for

Best for
Developers building LLM-driven futures trading strategies

Use cases

  • Backtesting futures trading strategies with LLM agents
  • Integrating agent-based research via MCP server
  • Configuring reproducible experiments with typed Pydantic configs

Notes

Echolon is an LLM-agent-native backtest framework for futures research. It provides an MCP server, in-package skills, catalogued error codes, and typed Pydantic configurations. It serves as the production engine inside Qorka at DolphinQuant.

1 stars on GitHub. Last updated 2026-05-08. Licensed Apache-2.0.

Use cases

  • Backtesting futures trading strategies with LLM agents
  • Integrating agent-based research via MCP server
  • Configuring reproducible experiments with typed Pydantic configs

Pros

  • LLM-agent-native design enables flexible agent-driven backtesting
  • Typed Pydantic configs improve reliability and reproducibility
  • Catalogued error codes aid debugging and error handling

Cons

  • Very early stage with only 1 GitHub star, indicating limited adoption
  • Niche focus on futures research may not suit other asset classes
  • Small community and sparse documentation likely

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • LLM-agent-native design enables flexible agent-driven backtesting
  • Typed Pydantic configs improve reliability and reproducibility
  • Catalogued error codes aid debugging and error handling

Cons

  • Very early stage with only 1 GitHub star, indicating limited adoption
  • Niche focus on futures research may not suit other asset classes
  • Small community and sparse documentation likely