How do I get my Carta API credentials?

Go to the **Carta Developer Portal** at **developer.carta.com** and log in or register. Click **Create App**, fill in the app details (name, homepage URL, grant type, and required scopes), then click **View app details** to find your **Client ID** and **Client Secret**. Copy both values and paste them into the configuration below. Note: Carta's API program is invite-only — if you don't have access, email **developers@carta.com** to request it.

Can my AI agent tell me exactly how much equity remains in our option pool?

Yes. Ask your agent to pull the cap table and it returns the total authorized shares, shares issued, options granted, options exercised, and the remaining unallocated pool — giving you an instant snapshot of your equity position. Perfect for board meetings, fundraising conversations, or new-hire planning where you need the numbers immediately.

What if a new hire asks about their vesting schedule during onboarding?

Your AI agent can pull any employee's grant details including total shares granted, vesting start date, cliff date, monthly vesting rate, and shares already vested — so HR can answer equity questions instantly during the onboarding call without opening the Carta dashboard or asking Legal.

Can this handle companies with complex multi-round fundraising histories?

Yes. The integration retrieves the full cap table structure including Seed, Series A, B, C rounds and beyond, convertible notes, SAFEs, and all share classes. Perfect for late-stage startups preparing for IPO, companies running secondary sales, and legal teams performing due diligence on cap table complexity.

Carta MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Carta
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Carta through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Carta "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Carta?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Carta MCP Server

Connect Carta to your AI agent and manage your company's equity operations, stakeholder information, and compliance data conversationally.

Pydantic AI validates every Carta tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Cap Table Queries — Retrieve your company's capitalization table including shares outstanding, share classes, and ownership percentages.
Equity Grants — List active stock option grants, vesting schedules, exercise windows, and grant statuses.
409A Valuations — Access your latest 409A valuation data and fair market values for compliance reporting.
Stakeholder Directory — Query your shareholder registry to find individual equity positions and contact details.

The Carta MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Carta to Pydantic AI via MCP

Follow these steps to integrate the Carta MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Carta with type-safe schemas

Why Use Pydantic AI with the Carta MCP Server

Pydantic AI provides unique advantages when paired with Carta through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Carta integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Carta connection logic from agent behavior for testable, maintainable code

Carta + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Carta MCP Server delivers measurable value.

Type-safe data pipelines: query Carta with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Carta tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Carta and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Carta responses and write comprehensive agent tests

Carta MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Carta to Pydantic AI via MCP:

get_cap_table

Get the full cap table

get_company

Get company details

list_companies

List all companies

list_convertibles

List convertible notes and SAFEs

list_funding_rounds

List funding rounds

list_option_plans

List stock option plans

list_securities

List all securities

list_share_classes

with liquidation preferences and conversion rights. List share classes

list_stakeholders

List all stakeholders

list_valuations

List 409A valuations

Example Prompts for Carta in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Carta immediately.

"Show me our current cap table summary."

"What's our latest 409A valuation?"

"How many shares has João Paulo vested so far?"

Troubleshooting Carta MCP Server with Pydantic AI

Common issues when connecting Carta to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Carta + Pydantic AI FAQ

Common questions about integrating Carta MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Carta MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.