How to Use the Saysimple MCP in Pydantic AI

Q: Can Pydantic AI fetch my active Saysimple messaging channels?

Yes, the agent calls listchannels to retrieve all active WhatsApp and SMS channels. The response is parsed into typed Python objects for safe handling in your application logic.

Q: How does Pydantic AI handle WhatsApp templates?

The agent runs listtemplates to get a list of approved message formats. It then uses gettemplate to validate the specific fields before formatting your message payload.

Build type-safe messaging workflows using Pydantic AI to validate Saysimple templates and contact data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Saysimple MCP to Pydantic AI

Create your Vinkius account to connect Saysimple 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 Saysimple with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe contact management with Pydantic AI

The `get_contact` tool retrieves customer records and validates them against strict Pydantic schemas before your agent processes the data over this MCP connection. This prevents malformed phone numbers or missing fields from crashing your pipeline. If a contact does not exist, the agent runs `create_contact` to write the new record. Pydantic AI guarantees that every field in the payload matches your strict database constraints before execution.

Strict schema validation for Saysimple MCP Server

The `send_message` tool requires a JSON string payload containing your template variables. Pydantic AI compiles this payload, verifying that every required variable matches the template schema exactly. The agent runs `get_template` to fetch the expected structure from the API. It then runs runtime checks against this structure, failing loudly if your code attempts to send an invalid parameter.

Deterministic chat routing and monitoring

The `assign_chat` tool updates conversation ownership based on agent availability rules. The agent parses active conversations with `list_chats` to identify unassigned messages that need attention. To keep the integration stable, the agent monitors configuration state using `list_webhooks`. If a webhook configuration changes, the runtime validation catches the structural drift immediately.

Setup guide

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

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

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

Use the MCPToolset class with your Vinkius HTTP endpoint URL. Pass this toolset instance to your Agent constructor to expose all eleven messaging tools to your model.

Pydantic AI intercepts the response and validates it against the tool's schema. If there is a mismatch, the agent raises a validation error immediately instead of proceeding with corrupted data.

Yes, the agent calls `list_channels` to retrieve all active WhatsApp and SMS channels. The response is parsed into typed Python objects for safe handling in your application logic.

The agent runs `list_templates` to get a list of approved message formats. It then uses `get_template` to validate the specific fields before formatting your message payload.

Your API token is stored securely in the Vinkius credential manager and injected into the ephemeral V8 Isolate sandbox. It never touches your local environment or the LLM context directly.

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