How to Use the FlowUs MCP in Pydantic AI

Q: How do I initialize the FlowUs MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class with your Vinkius server URL. Pass this toolset into the Agent constructor to expose the workspace tools.

Q: How does this integration protect sensitive page content?

Page text retrieved through getpage bypasses external logging entirely. The toolset executes locally in your Python shell, ensuring that proprietary documentation stays within your runtime boundaries.

Validate every FlowUs database row and page update at runtime using type-safe Pydantic AI agent MCP toolsets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowUs MCP to Pydantic AI

Create your Vinkius account to connect FlowUs 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 FlowUs with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe database queries with Pydantic AI

This MCP Server exposes `query_database` to let you fetch database records with strict runtime validation. When your agent calls this tool or runs `get_database`, the returned JSON matches your Pydantic models exactly. If the workspace schema changes unexpectedly, the agent fails loudly at runtime instead of corrupting your local state. This prevents silent failures when writing back to the workspace using `create_database_row`.

Strict page structure and block validation

Your agent updates documentation by calling `update_page` and `create_page` only after validating the payload against strict schemas. The unified `MCPToolset` class handles the connection to your Vinkius server over HTTP. When reading page contents using `get_page` or `list_blocks`, the framework parses the block types into typed Python objects. This structure ensures your agent never tries to parse an unexpected format under the underlying MCP specification.

Secure workspace audits and user verification

The agent audits your workspace by querying `list_users` and `list_pages` to verify team permissions. The model-agnostic nature of the framework lets you use any LLM to evaluate the validated data. Because the tool responses are structured, your agent can reliably parse the page tree. It flags missing fields or undocumented pages without risk of hallucinating structural relationships.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class with your Vinkius server URL. Pass this toolset into the `Agent` constructor to expose the workspace tools.

The framework raises a validation error immediately when parsing the `list_blocks` response. This stops the execution flow, preventing the agent from making incorrect assumptions based on bad data.

Yes. Your agent validates the row data against your Pydantic model before calling `create_database_row`, ensuring that only correctly formatted data enters your workspace.

Yes, the server runs on the Vinkius hosting platform. Your agent connects to this hosted MCP server on Vinkius over a secure HTTP or SSE transport using the `MCPToolset` class.

Page text retrieved through `get_page` bypasses external logging entirely. The toolset executes locally in your Python shell, ensuring that proprietary documentation stays within your runtime boundaries.

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