Investor Persona MCP Server
Provides AI-powered investor persona simulations through the MCP protocol, allowing users to access perspectives of notable venture capitalists like Fred Wilson and Peter Thiel for investment analysis.
README
Octagon Investor MCP Server
A Model Context Protocol (MCP) server that exposes AI-powered investor agent simulations through the MCP protocol, augmented with Octagon Private Markets data.
Features
Individual Investor Personas
- Fred Wilson (Union Square Ventures): Simulation of the NYC-based VC known for community-driven ventures
- Peter Thiel (Founders Fund): Simulation of the contrarian investor focused on disruptive technologies
Octagon Private Markets Data Agents
- Private Market Agents: Provides private markets data
Installation
Prerequisites
- Python 3.11+
- uv package manager
- OpenAI API key
- Octagon API key
Install via Smithery
npx -y @smithery/cli install @octagonai/investor-mcp-server --client claude
Claude Desktop Configuration
"mcpServers": {
"investor-persona-mcp-server": {
"command": "uvx",
"args": ["investor-persona-mcp-server"],
"env": {
"OPENAI_API_KEY": "your-openai-key-here",
"OCTAGON_API_KEY": "your-octagon-key-here",
"OCTAGON_BASE_URL": "https://api-gateway.octagonagents.com/v1"
}
}
}
Implementation Details
Persona Configuration
Investor personas are defined through markdown files containing:
- Investment philosophy
- Psychological profile
- Historical track record
- Decision-making patterns
- Communication style preferences
Customization Options
- Add new investor personas by creating markdown profiles
- Implement custom interaction patterns between personas
- Enhance orchestration logic for complex multi-perspective analysis
Configuration
Environment variables:
OPENAI_API_KEY: Required for AI model accessOCTAGON_API_KEY: Required for Octagon API accessOCTAGON_BASE_URL: Base URL for Octagon API (default: "https://api-gateway.octagonagents.com/v1")MCP_TRANSPORT: Transport protocol (default: "stdio")PERSONAS_DIR: Path to investor profiles (default: "./investors")
Development
# Clone repo
git clone https://github.com/octagonai/investor-mcp-server.git
cd investor-persona-mcp-server
# Setup environment
uv venv
source .venv/bin/activate
uv sync --dev
# Run with SSE transport
export OPENAI_API_KEY=your-openai-key
export OCTAGON_API_KEY=your-octagon-key
uv run mcp dev src/agents_mcp_server/server.py
Test via MCP Inspector at http://localhost:5173
License
MIT
investor-mcp
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。