How to Use the Carta MCP in OpenAI Agents SDK

Build production agents that manage Carta equity data using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Carta MCP to OpenAI Agents SDK

Create your Vinkius account to connect Carta to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Carta with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Real-Time Cap Table Data

Give your agent direct access to your company's ownership structure. It can call `get_cap_table` for a full breakdown or use `list_stakeholders` to check for a specific investor. This lets you build specialized agents that know exactly who owns what. Because you're using the OpenAI Agents SDK, you get guardrails that validate actions before they run. That means an agent built to monitor valuations with `list_valuations` can't accidentally try to modify records. It's a layer of safety that matters when you move from prototype to production.

Track Funding and Securities

Your agent can now monitor your company’s financial instruments. It can call `list_funding_rounds` to see historical raises or use `list_convertibles` to check on outstanding SAFEs and notes. This isn't just a static report; it's live data for your agent to act on. This is where the SDK's multi-agent design really pays off. You can have one agent watch for new convertibles, while another tracks option pool usage with `list_option_plans`. They can hand off tasks, and the SDK's built-in tracing gives you a full audit trail in the OpenAI dashboard.

Your Carta MCP Server, Ready for Agents

Forget writing custom API clients. The OpenAI Agents SDK automatically discovers every tool this Carta server exposes. Your agent instantly knows how to use `get_company` for official details or `list_share_classes` to check liquidation preferences. This isn't just about saving time. By setting `cacheToolsList=True` during setup, your production agents start faster after their first run. You're building a real product, and this MCP server gives your agents the direct Carta access they need to do their job.

Setup guide

Set up Carta MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Carta tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Carta tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Carta tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Carta Agent",
            instructions="You have access to Carta tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Carta. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Carta now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Carta MCP in OpenAI Agents SDK

It connects through this Vinkius-managed MCP Server. You pass the server's URL to `MCPServerStreamableHttp` in your Python code, and the SDK handles the rest—tool discovery, execution, and response handling.

Yes, by design. You build specialized agents that are only given the logic to call the tools they need for their specific job. The SDK's guardrails then help enforce those boundaries by validating actions before they run, preventing your `list_valuations` agent from calling other tools.

Yes. Your connection to the MCP server is encrypted, and Vinkius manages the authentication token. The OpenAI SDK adds its own safety layer with guardrails that can check an agent's intended action before it ever runs against the Carta data.

You skip the boilerplate. The SDK and this server work together so your agent understands how to query Carta's cap table and securities out of the box. You get to focus on your agent's logic, not on writing and maintaining HTTP request code.

The connection is between your agent, Vinkius, and Carta. Vinkius uses an ephemeral, zero-trust sandbox that is destroyed after each request. Your cap table and stakeholder information are never stored or seen by anyone.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript