How to Use the Kontak MCP in Pydantic AI

Q: How do I configure Kontak with Pydantic AI?

Install the pydantic-ai-slimmcp package. Initialize an MCPToolset with your HTTP endpoint URL, and pass it to the toolsets array when building your Agent.

Q: What happens if the Kontak API returns unexpected message data to Pydantic AI?

The framework catches it instantly. If listkontakmessages returns a payload that breaks your Pydantic schema, the agent halts and throws a loud validation error.

Q: Can Pydantic AI read my predefined Kontak templates?

Yes, by executing listkontaktemplates. The agent parses the template structures so it knows exactly which variables to inject before sending an outbound text.

Connect Kontak to Pydantic AI via MCP. Send SMS and manage contacts with strict runtime validation and zero silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontak MCP to Pydantic AI

Create your Vinkius account to connect Kontak 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 Kontak with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe SMS delivery

The `send_outbound_sms` tool executes text messages through the MCP Server with strict parameter validation. Pydantic AI ensures the agent passes a properly formatted phone number and string before the request ever hits the Kontak API. If the model hallucinates a parameter, the framework throws a validation error and stops execution. You then use `get_message_details` to confirm the exact delivery status of valid requests.

Fetch contacts into Pydantic models

Retrieving user data requires the `list_kontak_contacts` and `get_contact_details` tools. The agent requests the records, and Pydantic AI maps the JSON response directly into your predefined Python classes. Missing fields trigger immediate errors. The agent can also pull `list_kontak_tags` to categorize these contacts, ensuring your local database stays perfectly synced with the remote server.

Audit Kontak MCP Server settings

The `get_kontak_account_info` tool exposes your current billing and configuration state. Your agent reads this data to ensure you have enough credits before running a massive text campaign. For security checks, it calls `list_kontak_webhooks` and `get_kontak_audit_logs`. The framework validates the webhook URLs and event timestamps, failing loudly if the API returns malformed data structures.

Setup guide

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

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

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

Install the pydantic-ai-slim[mcp] package. Initialize an MCPToolset with your HTTP endpoint URL, and pass it to the toolsets array when building your Agent.

The framework catches it instantly. If list_kontak_messages returns a payload that breaks your Pydantic schema, the agent halts and throws a loud validation error.

Yes, by executing list_kontak_templates. The agent parses the template structures so it knows exactly which variables to inject before sending an outbound text.

Pydantic AI is completely model-agnostic. You can route your send_outbound_sms calls through Anthropic, Gemini, or a local Llama model without changing your toolset code.

Your application reads sensitive system events and admin actions through the MCP tools. The Vinkius infrastructure enforces a zero-trust model, meaning the server authenticates the single endpoint token and drops the connection the moment the log transfer finishes.

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