finance-trading-ai-agents-mcp and mcp-server

Both tools provide MCP servers for AI agent-based trading, making them competitors, with the first being a more general-purpose financial analysis platform and the second specifically focused on Hyperliquid trading intelligence.

mcp-server
46
Emerging
Maintenance 6/25
Adoption 14/25
Maturity 14/25
Community 21/25
Maintenance 13/25
Adoption 3/25
Maturity 18/25
Community 12/25
Stars: 96
Forks: 34
Downloads: 214
Commits (30d): 0
Language: Python
License:
Stars: 3
Forks: 1
Downloads:
Commits (30d): 0
Language: JavaScript
License: MIT
No License
No risk flags

About finance-trading-ai-agents-mcp

aitrados/finance-trading-ai-agents-mcp

A comprehensive, free MCP server designed specifically for financial analysis and quantitative trading. This specialized platform offers one-click local deployment with a sophisticated department-based architecture that mirrors real financial company operations.

Provides real-time streaming OHLC data, technical indicators, and broker integration for order placement—all callable directly by LLMs through standardized MCP tools. Implements a local RPC/PubSub service enabling cross-process and cross-language communication, with WebSocket support for synchronized data feeds across multiple clients and custom trading algorithms.

About mcp-server

Coinversaa/mcp-server

Hyperliquid trading intelligence for AI agents — cohort analytics, liquidation heatmaps, trader profiling, and real-time market data across 710K+ wallets.

Implements a Model Context Protocol (MCP) server that exposes 30 tools for querying Hyperliquid's on-chain data—including behavioral wallet cohorts (8 PnL tiers, 8 size tiers), liquidation heatmaps, and multi-dex market coverage across 8 builder DEXes trading commodities, stocks, and perps. Deploys via `npx` with optional API key authentication, integrating directly into Claude Desktop, Cursor, and Claude Code without local setup. Free tier provides 7 tools with IP-based rate limits; full access unlocks trader profiling, closed position history, and cohort-level bias analytics across 710K+ wallets.

Scores updated daily from GitHub, PyPI, and npm data. How scores work