How to Use the Gmelius MCP in Pydantic AI

Q: How do I register the Gmelius MCP Server with Pydantic AI?

You use the MCPToolset class pointing to your Vinkius HTTP endpoint and pass the MCP Server to your Pydantic AI Agent. The framework handles the connection and validates all tool schemas dynamically at runtime.

Q: How do I verify the connection status using Pydantic AI?

You can call checkgmeliusstatus within your startup sequence. The framework validates the status payload, ensuring your API key and connection are fully operational before starting your main agent loop.

Build type-safe email automation using Pydantic AI to validate every Gmelius 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 Gmelius MCP to Pydantic AI

Create your Vinkius account to connect Gmelius 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 Gmelius with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Gmelius MCP Server Data at Runtime

The `list_gmelius_conversations` tool retrieves your shared inbox threads, which the MCP Server exposes and Pydantic AI immediately parses into strict Python schemas. If the Gmelius API payload contains unexpected fields, the Pydantic AI framework raises a validation error instantly instead of letting corrupted data pass to your model. When fetching specific thread details via `get_gmelius_conversation`, your Pydantic AI agent relies on these strict types to build replies. This guarantees that variables like sender addresses and timestamps are perfectly formatted before your agent processes them.

Type-Safe Board Management with Pydantic AI

The `list_gmelius_boards` tool returns a structured list of your team's collaborative workspaces directly to your Pydantic AI agent. Pydantic AI validates the board metadata, allowing your agent to safely navigate columns and assignees without risking runtime crashes. To add tasks, the agent calls `create_gmelius_card` using validated input models. Because the Pydantic AI framework enforces strict type constraints, you can be certain that every card added to your Kanban boards matches your team's schema.

Extract Email Templates Safely

The `list_gmelius_templates` tool pulls your shared message templates into your local Pydantic AI runtime. Pydantic AI ensures that template placeholders and variables match your application's expected types before the agent attempts to fill them. Your agent uses `list_gmelius_sequences` to verify active email tracks in Gmelius. If the sequence configuration changes on the Gmelius side, Pydantic AI catches the structural drift immediately, protecting your production pipelines from silent failures.

Setup guide

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

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

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

You use the `MCPToolset` class pointing to your Vinkius HTTP endpoint and pass the MCP Server to your Pydantic AI Agent. The framework handles the connection and validates all tool schemas dynamically at runtime.

The framework will raise a validation error immediately, stopping execution before the bad data can corrupt your application state. This prevents your agent from making decisions based on malformed email or card structures.

Yes. Pydantic AI is model-agnostic, meaning you can run the validated Gmelius tools—like reading conversations via `list_gmelius_conversations`—using local models or any commercial API.

You can call `check_gmelius_status` within your startup sequence. The framework validates the status payload, ensuring your API key and connection are fully operational before starting your main agent loop.

The server accesses your shared templates and board cards using secure OAuth tokens managed by Vinkius. No email content or template text is stored on disk, keeping your team's internal communications strictly private.

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