Focus Admin MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Focus Admin through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
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 Focus Admin "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in Focus Admin?"
)
print(result.data)
asyncio.run(main())
* 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 Focus Admin MCP Server
Connect Focus Admin to any AI agent and access advanced fiscal management tools — send Correction Letters (CC-e), inutilize NF-e numbering, distribute DF-e documents, download XMLs and DANFEs, and list all invoices by period through natural conversation.
Pydantic AI validates every Focus Admin tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through 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
- Send CC-e — Issue Correction Letters for authorized NF-e with minor errors
- Cancel CC-e — Cancel previously sent Correction Letters
- Inutilize Numbering — Mark damaged or lost NF-e numbering ranges as unused
- Download XML & DANFE — Retrieve authorized NF-e XML documents and DANFE PDFs
- Distribute DF-e — Query available DF-e documents for your CNPJ by NSU
- List by Period — Retrieve all NF-e or NFS-e issued or received within a date range
- Download Event XML — Get XML for specific NF-e events (manifestations, CC-e, etc.)
The Focus Admin 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 Focus Admin to Pydantic AI via MCP
Follow these steps to integrate the Focus Admin 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 Focus Admin with type-safe schemas
Why Use Pydantic AI with the Focus Admin MCP Server
Pydantic AI provides unique advantages when paired with Focus Admin 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 Focus Admin integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Focus Admin connection logic from agent behavior for testable, maintainable code
Focus Admin + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Focus Admin MCP Server delivers measurable value.
Type-safe data pipelines: query Focus Admin with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Focus Admin tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Focus Admin and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Focus Admin responses and write comprehensive agent tests
Focus Admin MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect Focus Admin to Pydantic AI via MCP:
cancel_cc_e
Cancel a previously sent CC-e
distribute_dfe
Distribute DF-e documents (consult NSU)
download_event_xml
Download XML for a specific NF-e event
download_nfe_danfe
Download NF-e DANFE PDF
download_nfe_xml
Download NF-e XML document
inutilize_numbering
Inutilize a range of NF-e numbering
list_nfe_by_period
List NF-e documents by period
list_nfse_emitted
List NFS-e emitted by the company
list_nfse_received
List NFS-e received (tomadas) by the company
send_cc_e
Send a Correction Letter (CC-e) for NF-e
Example Prompts for Focus Admin in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Focus Admin immediately.
"Send a CC-e for NF-e REF-001 correcting the buyer's phone number."
"Inutilize NF-e numbering from 1000 to 1050 for series 1, model 55, year 2026."
"List all NF-e issued by CNPJ 12.345.678/0001-00 from 2026-03-01 to 2026-03-31."
Troubleshooting Focus Admin MCP Server with Pydantic AI
Common issues when connecting Focus Admin to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiFocus Admin + Pydantic AI FAQ
Common questions about integrating Focus Admin MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
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?
Can I switch LLM providers without changing MCP code?
Connect Focus Admin with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Focus Admin to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.
