How to Use the 8x8 MCP in Pydantic AI

Q: How do I connect the 8x8 MCP Server to Pydantic AI?

Install the slim package with the MCP extra. Initialize MCPToolset pointing to your Vinkius endpoint URL, and pass it directly into the toolsets argument when defining your agent.

Trigger 8x8 SMS, voice calls, and OTPs directly from Pydantic AI using this managed MCP Server with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 8x8 MCP to Pydantic AI

Create your Vinkius account to connect 8x8 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 8x8 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Messaging with the 8x8 MCP Server

Sending text and chat messages requires knowing exactly what the provider returned. When your agent calls `send_sms` or `send_chat_message`, Pydantic AI forces the API response through rigid schema checks. If the delivery payload mutates unexpectedly, the framework throws a hard validation error instead of silently swallowing bad data. You can immediately follow up by polling `get_sms_status` to confirm receipt. Because this setup cares about correctness above all else, your Python code knows with absolute certainty whether that critical notification actually reached the user's phone.

Trigger Voice Calls and OTP Pipelines

Building two-factor authentication flows is trivial when your models can talk directly to telecom infrastructure. Your application can dispatch a code using `send_verification` and then validate the user's input against the provider using `check_verification`. Sometimes text isn't enough. Developers can trigger automated text-to-speech alerts via `send_voice_message` for urgent system incidents. The agent then hits `get_call_status` to find out if the recipient actually picked up or sent it straight to voicemail.

Track Balances Across Telecom Accounts

Running out of credits mid-execution breaks production pipelines. Before kicking off a massive notification blast via MCP, your agent can run `get_account_balance` to ensure sufficient funds exist. Agencies managing multiple client phone numbers need visibility into specific silos. Fetching the full roster via `list_sub_accounts` gives your code the exact identifiers required to route billing accurately. We also included `check_8x8_status` just to confirm the API endpoint is awake before doing anything else.

Setup guide

Set up 8x8 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": {
        "8x8-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to 8x8 tools.",
)

result = await agent.run("List recent 8x8 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 8x8. 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 8x8 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 8x8 MCP in Pydantic AI

Install the slim package with the MCP extra. Initialize `MCPToolset` pointing to your Vinkius endpoint URL, and pass it directly into the `toolsets` argument when defining your agent.

Yes. If the telecom provider returns an unexpected schema for a failed text, the framework fails loudly. You catch the validation error in Python rather than dealing with silent corruption.

Any model supported by the framework can run these communication tools. Developers often use local LLMs via Ollama to trigger text messages, keeping orchestration entirely local while hitting the remote telecom API.

No. Vinkius handles the underlying provider credentials for the MCP Server connection. Your Python code just needs a single endpoint token to authorize the traffic.

Your phone numbers, OTP codes, and raw SMS content run through a V8 Isolate Sandbox on Vinkius. The environment is strictly ephemeral and zero-trust, meaning memory wipes completely the second your text message dispatches.

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