How to Use the Beekeeper MCP in Pydantic AI

Q: What's the setup for Pydantic AI and the Beekeeper MCP server?

It's straightforward. You instantiate MCPToolset with the Vinkius server URL and add it to the toolsets list when you create your Agent. Pydantic AI handles the rest, making the Beekeeper tools available to the LLM.

Add type-safe Beekeeper tools to your Pydantic AI agent. Manage users and posts with guaranteed data correctness for any LLM.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beekeeper MCP to Pydantic AI

Create your Vinkius account to connect Beekeeper 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 Beekeeper with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Interact with Beekeeper Posts and Streams

This toolset lets your agent read from and write to Beekeeper streams. Use `list_streams` to get a list of channels, then `list_posts` to fetch content. Every response is validated against a Pydantic model, so you know the data structure is exactly what your agent expects. When your agent uses `create_post`, the request is also structured and validated. If the Beekeeper API ever changes or returns something unexpected, Pydantic AI will raise a `ValidationError` immediately. No silent failures or corrupted data getting into your system.

Find and Manage Beekeeper Users

Your agent can safely query your Beekeeper user base. Tools like `list_users` and `search_users` return lists of users that are parsed into Pydantic models. You get structured objects, not just raw JSON dictionaries. The `get_user` tool fetches a specific user's profile, and again, the output is strictly validated. This means your agent can reliably work with user IDs, names, and emails without you having to write a bunch of defensive code to handle missing fields or wrong data types.

A Type-Safe MCP Server for Messaging

Give your agent the ability to send direct messages using the `send_message` tool. Pydantic AI ensures the arguments you pass—like the user ID and message content—are correctly typed before the request is even sent. This catches bugs early. When reading conversation history with `list_messages`, the response is rigorously checked. If a message is missing a timestamp or has a null author ID, your code will know about it instantly. This MCP integration makes it possible to trust the data your agent is working with.

Setup guide

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

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

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

Pydantic AI automatically converts the JSON response from each Beekeeper tool into a strongly-typed Pydantic model. If the data doesn't match the expected schema—for example, a field is missing from a `get_user` call—it raises a validation error. This guarantees data integrity.

Yes. The Beekeeper MCP toolset is model-agnostic. As long as your model can handle function calling, you can use it with Pydantic AI to call tools like `create_post` or `list_users`, whether you're using OpenAI, Anthropic, or a model running on your own machine.

It's straightforward. You instantiate `MCPToolset` with the Vinkius server URL and add it to the `toolsets` list when you create your `Agent`. Pydantic AI handles the rest, making the Beekeeper tools available to the LLM.

It retrieves basic information about your Beekeeper instance, like its name and URL. For a Pydantic AI agent, this is useful for ensuring the agent is connected to the correct tenant before it starts performing actions. The response is, of course, a validated model.

Your Beekeeper data, including user details, post content, and private messages, is processed in a secure, ephemeral V8 sandbox. Your auth token is managed by Vinkius for the duration of the call and is never stored. The data itself is not logged or retained after your tool call completes.

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