How to Use the Cometly MCP in Pydantic AI

Q: How do I set up the Cometly MCP Server in Pydantic AI?

Install the library using pip install 'pydantic-ai-slimmcp' and initialize MCPToolset with your Vinkius HTTP endpoint. Pass the toolset object into your Agent's toolsets list.

Build type-safe attribution agents with Pydantic AI and the Cometly MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cometly MCP to Pydantic AI

Create your Vinkius account to connect Cometly 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 Cometly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Cometly campaign data with Pydantic AI

The `get_campaign_stats` tool returns performance metrics that are validated against strict schemas at runtime. If the API returns unexpected data types, your agent fails immediately to prevent corrupted marketing reports. Running `list_campaigns` ensures you get a clean, typed list of your active ad sets. This guarantees your downstream calculations always receive valid floats and strings.

Type-safe conversion tracking and event logging

The `track_event` tool enforces strict input validation before sending conversion data to your dashboard. Your agent cannot fire malformed payloads, keeping your attribution model clean. With `track_purchase` and `track_lead`, every parameter is checked against Pydantic models before execution. This stops invalid currency codes or missing email fields from ruining your tracking.

Inspect customer journeys with zero silent errors

The `list_contacts` tool fetches customer journey touchpoints into strongly-typed Python structures. Your agent parses complex multi-touch paths knowing every field matches your exact schema. Using `list_events` alongside this data lets you build reliable attribution pipelines. You avoid the silent failures and hallucinated fields common in untyped agent frameworks.

Setup guide

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

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

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

Install the library using pip install 'pydantic-ai-slim[mcp]' and initialize MCPToolset with your Vinkius HTTP endpoint. Pass the toolset object into your Agent's toolsets list.

Pydantic AI validates all returned JSON against strict schemas. If a field mismatch occurs, the agent catches the validation error instantly, preventing silent data corruption.

Yes, this setup is model-agnostic. You can run local models or commercial APIs while maintaining strict type safety for all your tracking tools.

Yes, the toolset supports both Streamable HTTP and SSE transports. This allows you to connect to your hosted server on Vinkius using standard web protocols.

Your customer journey files and contact records are queried through isolated, zero-trust environments. Vinkius routes your MCP requests without keeping logs of your raw customer emails or phone numbers.

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