by OctagonAI
Provides AI‑driven venture‑capitalist personas that can evaluate pitches, simulate diligence, negotiate term sheets, and continuously incorporate real‑time deal, valuation, and research data from Octagon Private Markets.
Octagon VC Agents offers programmable "VC brain" agents modeled after well‑known venture capitalists (e.g., Fred Wilson, Peter Thiel, Marc Andreessen). Each agent leverages OpenAI models and is constantly enriched with up‑to‑date market intelligence from Octagon Private Markets, enabling realistic investment‑focused conversations.
pip install octagon-vc-agents
or run it directly with pipx
).@octagon-marc-andreessen-agent
) within prompts to get pitch feedback, diligence outlines, term‑sheet negotiations, or portfolio mapping.Q: Do I need both API keys to run the server? A: Yes. The Octagon key grants market data access, while the OpenAI key powers the language model.
Q: Can I create my own VC persona?
A: Absolutely. Add a markdown file under src/octagon_vc_agents/investors/
following the existing format and reference it in prompts.
Q: Which platforms support Octagon VC Agents? A: Any client that can call an MCP server, including Claude Desktop, Cursor, Windsurf, and custom CLI setups.
Q: Is there a cost to use the agents? A: You only pay for the underlying OpenAI usage and any Octagon subscription you maintain; the server itself is open‑source under MIT.
Q: How are the agents kept up‑to‑date with market information? A: The server queries Octagon Private Markets in real time, injecting the latest deal and valuation data into each agent's reasoning process.
An MCP server that runs AI-driven venture capitalist agents (Fred Wilson, Peter Thiel, etc.), whose thinking is continuously enriched by Octagon Private Markets' real-time deals, valuations, and deep research intelligence. Use it to spin up programmable "VC brains" for pitch feedback, diligence simulations, term sheet negotiations, and more.
VC Agents are also fully integrated them in ChatGPT with a demo Octagon API key. Give them a try here: VC Agents GPT
These are AI-powered simulations inspired by notable venture capitalists. These personas are not affiliated with or endorsed by the actual individuals.
VC Agent Name | Description |
---|---|
octagon-marc-andreessen-agent |
Simulation of the tech-optimist investor known for "software eating the world" thesis and bold technology bets |
octagon-peter-thiel-agent |
Simulation of the venture capitalist & 'Zero to One' author who analyzes investments through the lens of monopoly theory and contrarian thinking |
octagon-reid-hoffman-agent |
Simulation of the LinkedIn founder-turned-investor known for network-effect businesses and blitzscaling philosophy |
octagon-keith-rabois-agent |
Simulation of the operator-investor known for spotting exceptional talent and operational excellence |
octagon-bill-gurley-agent |
Simulation of the analytical investor known for marketplace expertise and detailed market analysis |
octagon-fred-wilson-agent |
Simulation of the USV co-founder & veteran early-stage investor focused on community-driven networks and founder-first philosophies |
octagon-josh-kopelman-agent |
Simulation of the founder-friendly investor focused on seed-stage companies and founder development |
octagon-alfred-lin-agent |
Simulation of the operator-turned-investor known for consumer businesses and organizational scaling |
What you want from the agents | Copy-and-paste prompt |
---|---|
Deal critique | Ask @octagon-marc-andreessen-agent and @octagon-reid-hoffman-agent to evaluate {company website}'s latest funding round. Provide a detailed comparative table from their points of view. |
Qualify investor fit before the call | @octagon-alfred-lin-agent You're vetting my pre-seed startup: {one-sentence pitch}. In {deck.pdf}, you'll find our vision, team, and WAU chart. Give me a "meet/pass" decision and list the three metrics I should strengthen most before your partner vote on Monday. |
Thesis & metrics reality-check | @octagon-reid-hoffman-agent Here's our 10-slide deck and dashboard ({docs}). We currently have {X} weekly active users, {Y}% MoM WAU growth, and {Z}% retention over 8 weeks. Using your 14-day diligence lens, list the biggest metric gaps that would prevent you from issuing a term sheet, and suggest how we could close them within one quarter. |
Portfolio-intro mapping – warm leads for the next round | @octagon-fred-wilson-agent Based on your current portfolio in {data} and our focus (outlined in the one-pager below), identify four portfolio CEOs who could become design partners. For each CEO, draft a first-contact email from me that highlights mutual value. |
To use Octagon VC Agents, you will need two API keys:
To use VC Agents, you need to:
OCTAGON_API_KEY
valueYou also need an OpenAI API key to enable AI-powered features:
OPENAI_API_KEY
valueTo use Octagon VC Agents, you need pipx, a tool for installing and running Python applications in isolated environments.
Install pipx using Homebrew (recommended):
brew install pipx
pipx ensurepath
Or with pip:
python3 -m pip install --user pipx
python3 -m pipx ensurepath
Install pipx using pip:
python -m pip install --user pipx
python -m pipx ensurepath
After installation, restart your terminal so that the pipx
command is available.
To configure Octagon VC Agents for Claude Desktop:
claude_desktop_config.json
(Replace YOUR_OCTAGON_API_KEY_HERE
with your Octagon API key and YOUR_OPENAI_API_KEY_HERE
with your OpenAI API key):{
"mcpServers": {
"octagon-vc-agents": {
"command": "pipx",
"args": ["run", "--pip-args=\"--no-cache-dir\"", "octagon-vc-agents", "run"],
"env": {
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE",
"OCTAGON_API_KEY": "YOUR_OCTAGON_API_KEY_HERE"
}
}
}
}
Configuring Cursor Desktop 🖥️ Note: Requires Cursor version 0.45.6+
To configure Octagon VC Agents in Cursor:
env OCTAGON_API_KEY=YOUR_OCTAGON_API_KEY_HERE OPENAI_API_KEY=YOUR_OPENAI_API_KEY_HERE pipx run --pip-args="--no-cache-dir" octagon-vc-agents run
If you are using Windows and are running into issues, try
cmd /c "set OCTAGON_API_KEY=YOUR_OCTAGON_API_KEY_HERE && set OPENAI_API_KEY=YOUR_OPENAI_API_KEY_HERE && pipx run --pip-args='--no-cache-dir' octagon-vc-agents run"
Replace YOUR_OCTAGON_API_KEY_HERE
with your Octagon API key and YOUR_OPENAI_API_KEY_HERE
with your OpenAI API key.
After adding, refresh the MCP server list to see the new tools. The Composer Agent will automatically use VC Agents when appropriate, but you can explicitly request it by describing your investment research needs. Access the Composer via Command+L (Mac), select "Agent" next to the submit button, and enter your query.
Add this to your ./codeium/windsurf/model_config.json
:
{
"mcpServers": {
"octagon-vc-agents": {
"command": "pipx",
"args": ["run", "--pip-args=\"--no-cache-dir\"", "octagon-vc-agents", "run"],
"env": {
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE",
"OCTAGON_API_KEY": "YOUR_OCTAGON_API_KEY_HERE"
}
}
}
}
env OCTAGON_API_KEY=YOUR_OCTAGON_API_KEY_HERE OPENAI_API_KEY=YOUR_OPENAI_API_KEY_HERE pipx run --pip-args="--no-cache-dir" octagon-vc-agents run
pip install octagon-vc-agents
Investor personas are defined through markdown files containing:
For detailed information about Octagon Agents, including setup guides, API reference, and best practices, visit our documentation.
MIT
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by danny-avila
Provides a customizable ChatGPT‑like web UI that integrates dozens of AI models, agents, code execution, image generation, web search, speech capabilities, and secure multi‑user authentication, all open‑source and ready for self‑hosting.
by ahujasid
BlenderMCP integrates Blender with Claude AI via the Model Context Protocol (MCP), enabling AI-driven 3D scene creation, modeling, and manipulation. This project allows users to control Blender directly through natural language prompts, streamlining the 3D design workflow.
by pydantic
Enables building production‑grade generative AI applications using Pydantic validation, offering a FastAPI‑like developer experience.
by GLips
Figma-Context-MCP is a Model Context Protocol (MCP) server that provides Figma layout information to AI coding agents. It bridges design and development by enabling AI tools to directly access and interpret Figma design data for more accurate and efficient code generation.
by mcp-use
Easily create and interact with MCP servers using custom agents, supporting any LLM with tool calling and offering multi‑server, sandboxed, and streaming capabilities.
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
by lharries
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp that allows users to search, read, and send WhatsApp messages (including media) through AI models like Claude. It connects directly to your personal WhatsApp account via the WhatsApp web multi-device API and stores messages locally in a SQLite database.
by idosal
GitMCP is a free, open-source remote Model Context Protocol (MCP) server that transforms any GitHub project into a documentation hub, enabling AI tools to access up-to-date documentation and code directly from the source to eliminate "code hallucinations."
by Klavis-AI
Klavis AI provides open-source Multi-platform Control Protocol (MCP) integrations and a hosted API for AI applications. It simplifies connecting AI to various third-party services by managing secure MCP servers and authentication.