How to Use the Nimbata MCP in Pydantic AI

Q: How do I connect Nimbata to a Pydantic AI agent?

Install pydantic-ai-slimmcp and initialize MCPToolset pointing to your Vinkius gateway URL. Pass this toolset instance to your Agent's toolsets list to expose all 12 validation-ready tools via the MCP Server.

Q: How do I list active tracking numbers?

Your agent runs listnumbers to retrieve all active phone lines. The framework automatically parses the response into type-safe Python objects, making it easy to check destinations with getnumber.

Q: How does Pydantic AI secure call recordings fetched from Nimbata?

Raw call recordings retrieved via getcallrecording are validated against strict Pydantic schemas and streamed directly to your local application storage. The Vinkius MCP Server gateway uses isolated V8 sandboxes to handle the API connection, ensuring that caller phone numbers and audio files are never cached or exposed to external networks.

Enforce strict type safety on call tracking and attribution data using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbata MCP to Pydantic AI

Create your Vinkius account to connect Nimbata 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 Nimbata with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Call Data at Runtime with Pydantic AI

The `get_call_details` tool integrates with Pydantic AI to guarantee that every incoming call record matches your strict Python schemas over the Nimbata MCP Server. This ensures that caller metadata matches your expected data structures before the model ever sees it. If the API returns unexpected or malformed phone records, the framework raises a validation error immediately. This prevents your LLM from processing corrupted caller IDs or hallucinating call durations during automated audit cycles.

Type-Checked Campaign Provisioning

Your agent uses `create_source` to generate new dynamic tracking pools with strict input validation powered by Pydantic AI. The framework ensures that parameters like landing page URLs and routing numbers conform to your exact type definitions before hitting the API. After creation, the agent runs `get_source` to verify the setup against your internal database models. By using the unified `MCPToolset` class, you expose these schema-validated tools to any supported model, whether you run OpenAI, Anthropic, or local weights.

Fail-Safe Call Attribution Analytics

This integration uses `get_source_report` to compile marketing performance metrics without silent type mismatches in Pydantic AI. If a tracking source lacks conversion data, the validated response structure prevents the agent from making budgeting errors based on null values. The agent also runs `get_call_report` to track overall conversion trends over time. Before starting any analytical run, the agent calls `check_nimbata_status` to ensure the API gateway is fully operational and authenticated.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` pointing to your Vinkius gateway URL. Pass this toolset instance to your Agent's `toolsets` list to expose all 12 validation-ready tools via the MCP Server.

The framework raises a runtime validation error, stopping the agent from acting on corrupt data. This ensures that sensitive operations like analyzing call recordings via `get_call_recording` never ingest malformed payloads.

Yes, because Pydantic AI is model-agnostic. You can run a local model and expose Nimbata tools like `list_calls` or `search_calls` through the same type-safe MCP interface.

Your agent runs `list_numbers` to retrieve all active phone lines. The framework automatically parses the response into type-safe Python objects, making it easy to check destinations with `get_number`.

Raw call recordings retrieved via `get_call_recording` are validated against strict Pydantic schemas and streamed directly to your local application storage. The Vinkius MCP Server gateway uses isolated V8 sandboxes to handle the API connection, ensuring that caller phone numbers and audio files are never cached or exposed to external networks.

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