How to Use the Carta MCP in Google ADK

Connect Gemini agents to your Carta cap table with Google's ADK.

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 Google ADK

Create your Vinkius account to connect Carta to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Carta from Your Google Cloud Agent

This server gives your ADK-based agent a direct line to your Carta account. Your agent can run `get_cap_table` or `list_stakeholders` and pull the results right into your Google Cloud environment. No manual exports or data wrangling required. Now, feed that data into BigQuery. With a Gemini model's long-context window, your agent can analyze years of funding history from `list_funding_rounds` against other business data you already have stored in your Google Cloud project.

Analyze Equity and Valuations

Build an agent that actively monitors your company's equity structure. It can use `list_share_classes` to understand liquidation preferences and `list_option_plans` to track dilution from the employee pool. Since the Google ADK works with Vertex AI, you can trigger complex analysis pipelines. An agent could fetch the latest 409A data using `list_valuations`, then kick off a custom model in Vertex AI to forecast different fundraising scenarios.

Enterprise-Ready Carta MCP Server

Setting this up in your Google ADK project is simple. You instantiate an `McpToolset` with the server URL from Vinkius, and your `LlmAgent` now has a full set of tools for talking to Carta. For tighter control in an enterprise setting, the ADK lets you use a `tool_names` filter. This means you can expose only specific actions, like `get_company` details, to certain agents, while restricting access to sensitive tools like `get_cap_table`.

Setup guide

Set up Carta MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Carta tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Carta_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Carta tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Your Google ADK agent uses this MCP server to call tools like `list_securities`. The agent gets back structured data, which you can then have it write directly into a BigQuery table for large-scale analysis.

Yes. Because the Google ADK is a part of Google Cloud, you can use services like Cloud Scheduler and Cloud Functions to trigger your agent. You could have it run `list_convertibles` daily and send a notification if a new SAFE is issued.

It is. The MCP server itself runs in a zero-trust, ephemeral sandbox, and your connection is encrypted. The Google ADK is built for enterprise applications on Google Cloud, providing a secure foundation for your agents.

It's the native integration with the rest of Google Cloud. Your Gemini agent can pull data from Carta and immediately use it with BigQuery or Vertex AI without you needing to build and maintain separate data pipelines.

The server only processes the data your agent explicitly requests via tool calls. This includes your company's cap table, stakeholder lists, security details, and 409A valuation reports. Each request is handled in a temporary, isolated sandbox that is destroyed right after.

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