How to Use the ProTexting MCP in Pydantic AI

Q: How do I add ProTexting to a Pydantic AI project?

Install the pydantic-ai-slimmcp package. Initialize an MCPToolset with your HTTP endpoint and pass it into the toolsets array on your Agent instance. Do not use the deprecated MCPServerHTTP class.

Q: What happens if Pydantic AI gets a bad response from the ProTexting MCP Server?

The framework throws a strict validation error. If the checkprotextingstatus tool returns an unexpected payload structure, Pydantic AI halts the agent immediately rather than passing corrupted data downstream.

Q: Can Pydantic AI manage my ProTexting keywords?

Yes. Your agent can execute listkeywords to retrieve your active shortcode triggers. The response is strictly typed, so your Python logic can safely iterate over the keywords without checking for missing dictionary keys.

Build type-safe SMS automation with Pydantic AI and the ProTexting MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ProTexting MCP to Pydantic AI

Create your Vinkius account to connect ProTexting to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ProTexting with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe ProTexting Contact Management

Silent API failures ruin marketing databases. When your Pydantic AI agent calls `list_contacts` or `list_groups`, the framework validates the ProTexting JSON response against strict Pydantic schemas before your code ever touches it. If the API returns a string where an integer was expected, the agent fails loudly with a validation error. This guarantees that when you run `create_contact` or `delete_contact`, your application state matches reality perfectly.

Execute SMS Campaigns with Confidence

You cannot afford hallucinations when sending thousands of text messages. Your agent uses `send_bulk` and `send_sms`, and Pydantic AI ensures the phone number arrays and message payloads are formatted exactly as the schema demands. If a local LLM tries to hallucinate a fake parameter for `send_mms`, Pydantic AI catches it at runtime. The execution stops immediately, protecting your ProTexting budget and your sender reputation.

Validate Account Metrics with the MCP Server

Knowing your exact account limits prevents mid-campaign crashes. The agent calls `get_account` to fetch credit balances, and the framework forces that data into a typed model so you can safely write conditional logic against it. You can also track delivery success by running `get_message_status`. Because Pydantic AI is model-agnostic, you can swap from OpenAI to an open-source model while maintaining the exact same strict type checks on your delivery receipts.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package. Initialize an `MCPToolset` with your HTTP endpoint and pass it into the `toolsets` array on your Agent instance. Do not use the deprecated `MCPServerHTTP` class.

The framework throws a strict validation error. If the `check_protexting_status` tool returns an unexpected payload structure, Pydantic AI halts the agent immediately rather than passing corrupted data downstream.

Yes. Your agent can execute `list_keywords` to retrieve your active shortcode triggers. The response is strictly typed, so your Python logic can safely iterate over the keywords without checking for missing dictionary keys.

It works perfectly. Pydantic AI is model-agnostic. You can point your agent at a local Llama instance, and it will still enforce strict schema validation when calling `send_bulk` or `create_group`.

This integration processes mobile subscriber numbers, group IDs, and raw text message payloads. The server operates as an isolated process, meaning your API keys and contact lists stay within your local Python memory space. Pydantic AI only exposes the validated schemas to the LLM, keeping the actual transport layer entirely separate.

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