How to Use the TextGrid MCP in Pydantic AI

Q: How does Pydantic AI handle message history with TextGrid?

The agent can use listsmsmessages to pull a list of texts. Because the response is validated, you are guaranteed that every field—like timestamp or status code—exists and has the right data type.

Q: Can Pydantic AI check API health with TextGrid?

Yes. Running checkapihealth provides a structured, validated response about the server's current operational state. This prevents your agent from relying on potentially stale connection data.

Q: What tools does Pydantic AI use for account management with TextGrid?

It uses listapikeys to get a list of API keys, ensuring they are treated as strings. It also calls getaccountdetails, validating all fields like balance and user ID against your defined schema.

Q: Does Pydantic AI support listing voice call history with TextGrid?

The agent uses listvoicecalls to pull historical data. Since the output is type-safe, you can rely on specific fields like call duration or termination codes being present.

Q: What type of data does the Pydantic AI touch regarding data privacy with TextGrid?

The server touches account profile and balance data via getaccountdetails. This includes financial figures that your agent must correctly validate against defined numerical types.

Build type-safe messaging agents using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TextGrid MCP to Pydantic AI

Create your Vinkius account to connect TextGrid 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 TextGrid with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Get usage and account details.

When your agent needs to know the budget, it runs `get_account_details`. This returns validated fields for balance and profile. If a field is missing or wrong, your agent fails *loudly*. The tool also lets you check consumption with `get_usage_statistics`, ensuring that every returned cost record matches the expected schema.

Start calls and manage numbers.

The process of initiating a call is handled by `initiate_voice_call`. The agent expects structured output, so it validates key parameters like duration or target number. If you pass bad input, the agent stops. Need to find a number? It uses `list_account_addresses` to validate regional addresses before searching with `search_available_numbers`.

Check messaging status and history.

When you send an SMS or MMS, the agent calls `send_sms_message`. The result is wrapped in a Pydantic model, so you know instantly if the message was queued correctly. To review past comms, it can pull records using `list_sms_messages` and also retrieve detailed information for one specific text using `get_message_details`.

Setup guide

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

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

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

The agent can use `list_sms_messages` to pull a list of texts. Because the response is validated, you are guaranteed that every field—like timestamp or status code—exists and has the right data type.

Yes. Running `check_api_health` provides a structured, validated response about the server's current operational state. This prevents your agent from relying on potentially stale connection data.

It uses `list_api_keys` to get a list of API keys, ensuring they are treated as strings. It also calls `get_account_details`, validating all fields like balance and user ID against your defined schema.

The agent uses `list_voice_calls` to pull historical data. Since the output is type-safe, you can rely on specific fields like call duration or termination codes being present.

The server touches account profile and balance data via `get_account_details`. This includes financial figures that your agent must correctly validate against defined numerical types.

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