How to Use the ONES MCP in Pydantic AI

Q: Can I use Pydantic AI to safely assign tasks to team members inside ONES?

Yes, you can use listmembers to fetch active users and validate their IDs against your own schema. This ensures createtask always receives a valid assignee ID.

Build type-safe R&D agents with Pydantic AI that validate every ONES task and workflow change at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to Pydantic AI

Create your Vinkius account to connect ONES 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 ONES with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Enforce strict runtime validation for ONES tasks

Never worry about an agent corrupting your project board with malformed data when using `get_task_details` and `list_tasks`. Pydantic AI forces every response to conform to strict Python types. If the API returns something unexpected, the framework catches it instantly. This type safety is critical when calling `create_task` or `update_task`. The agent cannot pass invalid fields or incorrect user IDs because the runtime schema validation blocks the call before it hits your production tracker.

Verify R&D workflows programmatically

Project tracking systems are notorious for complex, rigid state machines, but your Pydantic AI agent can read the exact workflow steps using `list_workflows` and `list_task_types`. Because Pydantic AI is model-agnostic, you can swap your underlying LLM without rewriting your validation logic. The framework guarantees that the output of `get_project` or `get_org_info` is parsed correctly every single time.

Integrate the ONES MCP Server with zero fuss

Connecting your agent to the MCP server is straightforward using the unified `MCPToolset` class, giving your agent instant access to `list_members`. This setup avoids deprecated HTTP classes and keeps your codebase clean. Your agent gets instant access to all organization tools with full type hints in your IDE.

Setup guide

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

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

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

The framework wraps the server tools in Pydantic models. When the agent calls `get_task_details`, the response is parsed and validated against these models, raising immediate errors if the schema mismatches.

Yes, you can use `list_members` to fetch active users and validate their IDs against your own schema. This ensures `create_task` always receives a valid assignee ID.

It supports both Streamable HTTP and SSE transports. You configure this when initializing your `MCPToolset` pointing to the external server running on Vinkius.

The framework validates the arguments against the tool's schema before execution. The invalid call is blocked, and the agent receives a clear validation error so it can try again with correct parameters.

All data passing through the server—including user lists, task statuses, and workflow definitions—is processed inside isolated V8 sandboxes. Your credentials are never exposed, and connections use secure single-token authentication.

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