How to Use the Nubarium MCP in Pydantic AI

Q: How do I check my remaining requests?

Execute getapiusage within your agent flow to retrieve your current consumption metrics. The returned data is validated against a strict schema so your monitoring code won't break.

Type-safe validation of Mexican RFC, CURP, and corporate data within your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nubarium MCP to Pydantic AI

Create your Vinkius account to connect Nubarium 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 Nubarium with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Mexican companies with Pydantic AI

The `search_mex_companies` tool searches the Mexican corporate registry by name and returns structured candidate lists. This tool ensures that your agent only works with valid search results, failing loudly if the response schema does not match your expected structure. Once a company is identified, the agent uses `get_mex_company_details` to retrieve deep corporate records. Because Pydantic AI enforces type safety at runtime, any unexpected null fields or modified data types in the registry response are caught instantly, preventing data corruption in your database.

Validate RFC and CURP with this MCP Server

The `validate_mex_rfc` tool checks Mexican tax IDs against official records to confirm their validity and active status. This tool acts as an automated gatekeeper, ensuring that invalid RFC strings are rejected at the model boundary before they trigger downstream errors. For personal identity checks, `validate_mex_curp` pulls verified individual records directly into your agent's context. The type-safe schema validation ensures that your agent receives cleanly formatted strings for names, birthdates, and registration offices every single time.

Verify legal authority in Pydantic AI

The `validate_mex_legal_representative` tool checks if a given CURP is legally tied to a corporate RFC. This tool eliminates the risk of accepting unauthorized signers by providing a definitive verification status that your agent can trust implicitly. To monitor your system resources, you can call `get_api_usage` to verify your current request count against your subscription limits. This keeps your operational costs predictable while running automated compliance checks across your entire platform.

Setup guide

Set up Nubarium 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": {
        "nubarium-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Nubarium 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 Nubarium. 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 Nubarium 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 Nubarium MCP in Pydantic AI

Install the slim package with the MCP option and create an MCPToolset pointing to your server URL. Pass this toolset directly to your agent constructor to register the Mexican compliance tools.

The agent will raise a validation error at runtime if the data from this MCP Server to Pydantic AI does not match your schema. This prevents your agent from making decisions based on malformed or corrupted Mexican corporate records.

Yes, the framework is model-agnostic. You can use these Mexican registry tools with OpenAI, Anthropic, or local models as long as they support tool calling.

Execute `get_api_usage` within your agent flow to retrieve your current consumption metrics. The returned data is validated against a strict schema so your monitoring code won't break.

The MCP Server processes RFC, CURP, and company details using secure, ephemeral connections. No identity data is cached or logged on the server side, meeting strict compliance standards for sensitive Mexican personal records.

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