How to Use the Nimbleway MCP in Pydantic AI

Q: How do I initialize Nimbleway with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset instance with your HTTP endpoint and pass it to your agent. Ensure you use the unified toolset approach rather than the deprecated server classes.

Q: Can Pydantic AI handle Nimbleway rate limits?

Your agent reads the getaccountusage output and maps it to a strict Pydantic model. If the remaining bandwidth drops below your threshold, the system halts execution immediately.

Build type-safe web scrapers by connecting Pydantic AI to live search and extraction tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbleway MCP to Pydantic AI

Create your Vinkius account to connect Nimbleway 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 Nimbleway with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Markdown Parsing

The `extract_markdown` and `extract_html` tools return web content in predictable formats. Your agent runs `search_web` to find a target, then pulls the exact text required. Pydantic AI validates every single response against your predefined models. If a website changes its layout and the API returns unexpected data, the agent fails loudly. You get a strict validation error instead of silent data corruption.

Pydantic AI MCP Server Pipelines

The `list_pipelines` and `get_pipeline` tools expose your existing extraction configurations. Agents track the progress of these runs using `list_jobs` and `get_job`. You care about correctness. When the agent pulls job status, the framework ensures the response matches the exact schema. This MCP integration guarantees your code never processes hallucinated fields.

Validate Account Metrics

The `get_account_usage` and `get_me` tools report your bandwidth consumption. You check your routing setup with the `list_proxies` tool before initiating a massive scrape. The framework remains entirely model-agnostic. You swap between local models, Anthropic, or OpenAI, and the agent executes the exact same validation logic against the account metrics.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` instance with your HTTP endpoint and pass it to your agent. Ensure you use the unified toolset approach rather than the deprecated server classes.

Your agent reads the `get_account_usage` output and maps it to a strict Pydantic model. If the remaining bandwidth drops below your threshold, the system halts execution immediately.

Yes. The framework sends the tool schemas to any compatible model. Your local setup parses the requirements and calls the tools just like a hosted service would.

Pydantic AI throws explicit validation errors if the MCP tool response violates your schema. You check the stack trace to see exactly which field caused the failure.

Vinkius executes your proxy configurations and bandwidth metrics inside an isolated environment. The process requires a single auth token and leaves zero persistent footprint on our network.

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