How to Use the Asaas MCP in Pydantic AI

Q: Does Pydantic AI validate Asaas customer data?

Every piece of data returned by listcustomers gets checked against expected schemas. You won't deal with hallucinated fields or missing dictionary keys in your Python logic.

Build type-safe Asaas billing agents with Pydantic AI where every MCP payment response is strictly validated.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Asaas MCP to Pydantic AI

Create your Vinkius account to connect Asaas to Pydantic AI 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 Asaas with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Asaas MCP Server

Financial APIs demand absolute correctness. Silent failures in payment processing code destroy businesses. When your agent calls `create_payment` or `create_customer`, the framework validates the Brazilian payment gateway's response against strict models at runtime. If the API returns a string instead of a float for the charge amount, the agent fails loudly with a validation error.

Model-Agnostic Accounting

Locking your billing system to a single LLM provider creates unnecessary risk. This framework lets you swap underlying models without changing your tool logic. You test `list_subscriptions` and `get_balance` using a fast local model during development. Once deployed, you switch the agent to Anthropic or OpenAI to handle complex ledger reasoning, all while keeping the exact same toolset.

Unified Toolset Architecture

Managing multiple external integrations gets messy fast. The unified connection approach keeps your agent definition clean and predictable. Just install pydantic-ai-slim[mcp] and wrap your Vinkius endpoint in an MCPToolset. Pass that directly into the toolsets parameter, and the framework automatically exposes `list_transfers` and `get_account_check` to your model.

Setup guide

Set up Asaas MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "asaas-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Asaas tools.",
)

result = await agent.run("List recent Asaas transactions")
print(result.output)

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 Asaas. 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 Asaas 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 Asaas MCP in Pydantic AI

Install the slim package with the MCP extra. Create an MCPToolset pointing to your HTTP endpoint. Assign it to your agent's toolsets list to activate the integration.

Every piece of data returned by `list_customers` gets checked against expected schemas. You won't deal with hallucinated fields or missing dictionary keys in your Python logic.

The older HTTP-specific server classes are deprecated. Using MCPToolset gives you a future-proof way to connect to Vinkius endpoints over Streamable HTTP or SSE transports.

Yes, the framework is entirely model-agnostic. You'll trigger `list_payments` using open-source models just as easily as proprietary ones.

Recurring billing details and transfer amounts pass through a secure, ephemeral V8 Isolate Sandbox. Vinkius requires only one endpoint token to authenticate. We never inspect or store your financial models.

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