Can the AI generate a script with my actual proxy endpoints already inserted?

Yes. While prompting inside an IDE like Cursor, you can ask 'Write a Python script using my residential proxy endpoint.' The AI agent will call `list_residential_proxies` in the background, harvest the legit port numbers, and assemble runnable code on the spot.

Is it safe to pull network architecture metrics inside Claude AI?

Absolutely secure. The MCP protocol bridges interactions locally. At no setup phase does Vinkius cloud servers retrieve your Smartproxy metrics directly—the exchange passes via your local agent bridging right into Decodo's endpoint.

Can it tell me my remaining bandwidth limit?

Yes. Ask the bot 'How much target data do I have left?' and it will orchestrate the results of both `get_account_details` (which returns quota details) and `get_traffic_usage` (which exposes used data) to compute the remaining bytes in conversational form.

Decodo (Smartproxy) MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: Decodo (Smartproxy)
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Decodo (Smartproxy) through 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 Decodo (Smartproxy) "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Decodo (Smartproxy)?"
    )
    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 Decodo (Smartproxy) MCP Server

Connect your Decodo (Smartproxy) account to any AI agent to control your proxy endpoints, audit infrastructure, and track SERP/scraping data seamlessly. Interact with your server architecture and networking limits using natural language without jumping out of your IDE.

Pydantic AI validates every Decodo (Smartproxy) tool response against typed schemas, catching data inconsistencies at build time. Connect 9 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

Inventory Management — Effortlessly pull a list of active list_proxy_endpoints, list_datacenter_proxies, and list_residential_proxies
Live Bandwidth Monitoring — Run get_traffic_usage directly inside the AI prompt to see if you are about to hit your monthly data quota cap
Bot Statistics — Evaluate the health of your bots automatically by checking get_scraper_stats for eCommerce and SERP scrapers
Reselling & Accounts — Generate your list_subscriptions details, retrieve your general account health, or list all nested sub-users associated with the account

The Decodo (Smartproxy) MCP Server exposes 9 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 Decodo (Smartproxy) to Pydantic AI via MCP

Follow these steps to integrate the Decodo (Smartproxy) 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 9 tools from Decodo (Smartproxy) with type-safe schemas

Why Use Pydantic AI with the Decodo (Smartproxy) MCP Server

Pydantic AI provides unique advantages when paired with Decodo (Smartproxy) 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 Decodo (Smartproxy) integration code

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

Dependency injection system cleanly separates your Decodo (Smartproxy) connection logic from agent behavior for testable, maintainable code

Decodo (Smartproxy) + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Decodo (Smartproxy) MCP Server delivers measurable value.

Type-safe data pipelines: query Decodo (Smartproxy) with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Decodo (Smartproxy) tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Decodo (Smartproxy) and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Decodo (Smartproxy) responses and write comprehensive agent tests

Decodo (Smartproxy) MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect Decodo (Smartproxy) to Pydantic AI via MCP:

get_account_details

Retrieves Smartproxy account information

get_scraper_stats

Retrieves statistics for scraping APIs

get_traffic_usage

Retrieves traffic usage statistics

list_datacenter_proxies

Lists datacenter proxy configurations

list_dedicated_proxies

Lists dedicated proxy assignments

list_proxy_endpoints

Lists available proxy endpoints

list_residential_proxies

Lists residential proxy configurations

list_sub_users

Lists all proxy sub-users

list_subscriptions

Lists active proxy subscriptions

Example Prompts for Decodo (Smartproxy) in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Decodo (Smartproxy) immediately.

"Find all of our active datacenter proxy endpoints."

"Use Decodo and query my scraping success rate summary."

"Have we exceeded the traffic usage on the account?"

Troubleshooting Decodo (Smartproxy) MCP Server with Pydantic AI

Common issues when connecting Decodo (Smartproxy) to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Decodo (Smartproxy) + Pydantic AI FAQ

Common questions about integrating Decodo (Smartproxy) 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 Decodo (Smartproxy) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.