How to Use the Reportei MCP in Pydantic AI

Q: How does Pydantic AI handle the Reportei timeline?

Your agent can use addreporteievent to write new events and listreporteitimeline to retrieve them. The returned timeline events are automatically validated against the framework's internal schemas.

Build type-safe marketing agents with Pydantic AI and the Reportei MCP Server for bulletproof data validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Reportei MCP to Pydantic AI

Create your Vinkius account to connect Reportei 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 Reportei with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate Reportei metrics at runtime with Pydantic AI

This MCP Server provides the `get_reportei_metrics` tool to deliver structured marketing data that Pydantic AI validates against strict Python type schemas at runtime. When your agent calls for metrics, the framework ensures every integer, string, and float matches your expected data models. If an API integration returns unexpected or corrupted data, the framework fails loudly before any bad data reaches your database. This prevents silent execution failures when handling complex social media metrics.

Type-safe client and project management

Your agent can run the `list_clients` or `get_client` tools to retrieve validated profiles for your marketing accounts. Managing client directories requires structured data that won't break your application. By combining these outputs with `list_reportei_projects`, your type-safe agent can map projects to clients without risking null-pointer exceptions. Every dictionary returned by the server is parsed into a clean Python object.

Automate report generation with schema verification

Your agent calls the `create_report` tool to generate new client reports, and then uses `get_report_details` to verify the output. Generating reports manually is prone to human error, but automated tools need strict validation. Because the tools are integrated with MCPToolset, the responses from `list_reportei_reports` are parsed directly into Pydantic models. You can confidently build automated email delivery systems knowing the report metadata is fully validated.

Setup guide

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

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

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

Install the framework with the MCP extra and initialize MCPToolset using your Vinkius HTTP endpoint. Pass this toolset into your Agent constructor to give your model access to tools like `get_reportei_metrics`.

Pydantic AI will raise a validation error at runtime, preventing your agent from processing corrupt marketing data. This is ideal for production pipelines where data integrity is more important than speed.

Your agent can use `add_reportei_event` to write new events and `list_reportei_timeline` to retrieve them. The returned timeline events are automatically validated against the framework's internal schemas.

Yes, the framework is model-agnostic, meaning you can run your agent on local models or commercial APIs. The underlying MCP Server handles the tool execution regardless of which LLM you choose.

The server runs in an ephemeral, zero-trust sandbox that does not persist your client profiles or marketing metrics. It only queries the Reportei API in real-time when your agent requests data via `get_client`.

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