How to Use the Dexatel MCP in Pydantic AI

Q: How do I configure Dexatel for Pydantic AI?

Install pydantic-ai-slimmcp. Initialize MCPToolset with your HTTP endpoint URL, and pass it into the toolsets array of your Agent instance.

Q: How do I check a specific message status?

Give the agent access to getsmsmessagedetails. It fetches the exact delivery timeline and status flags for that specific transaction.

Q: Is my message content secure during execution?

Yes. When your agent reads text bodies via listsmsmessages, the data flows through an isolated V8 sandbox. The managed MCP connection uses zero-trust architecture, ensuring no persistent access remains after the script exits.

Use the Dexatel MCP Server with Pydantic AI to build type-safe agents that validate every SMS API response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dexatel MCP to Pydantic AI

Create your Vinkius account to connect Dexatel 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 Dexatel with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe SMS execution via Pydantic AI

The `send_sms_message` tool triggers outbound text messages with strict parameter validation. If the API expects a specific string format for the phone number, Pydantic AI enforces it. Before the agent commits to sending, it queries `get_account_balance_metadata` to verify sufficient funds. You avoid silent failures in production. If the balance check returns a malformed JSON payload, your agent crashes loudly with a validation error. You fix the schema mismatch immediately instead of letting a broken agent attempt thousands of bad requests.

Strict template and sender ID enforcement

The `list_authorized_sender_ids` tool pulls the exact list of virtual numbers you own. Your agent validates this list against a Pydantic model. It knows exactly which IDs are active and routes outbound messages through them based on your strict logic. Compliance is non-negotiable. The agent calls `list_sms_templates` to retrieve approved message formats from this MCP Server. Because Pydantic AI validates the response, you know the agent is working with exact template strings, eliminating the risk of hallucinated promotional text.

Audit failures and contact data

The `list_failed_sms_deliveries` tool fetches records of dropped messages. Your agent processes these failures through a strictly typed data pipeline. You get exact error codes and timestamps, never guessing why a specific carrier rejected your traffic. When auditing user interactions, the agent uses `get_contact_profile`. It retrieves the full history for a specific phone number. Combine this with `search_sms_by_content` to build an agent that safely searches for keywords and returns validated, structured reports.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Initialize `MCPToolset` with your HTTP endpoint URL, and pass it into the `toolsets` array of your Agent instance.

Immediately. If the API alters the response format for message details, the runtime validation fails with a clear error. You catch the drift before it corrupts your agent's logic.

Yes. The framework is model-agnostic. Run a local Llama model and still give it full access to these messaging tools.

Give the agent access to `get_sms_message_details`. It fetches the exact delivery timeline and status flags for that specific transaction.

Yes. When your agent reads text bodies via `list_sms_messages`, the data flows through an isolated V8 sandbox. The managed MCP connection uses zero-trust architecture, ensuring no persistent access remains after the script exits.

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