How to Use the Zeev MCP in Pydantic AI

Q: How do I check if a specific process is running using Zeev and Pydantic AI?

Use getrequest. Since the response must pass through Pydantic validation, you'll get clean, type-safe data confirming the workflow's state.

Q: Where can I find a list of all available workflows for Zeev and Pydantic AI?

The listprocesses tool gives you the definitive list. Every process definition returned is validated, so your agent trusts the schema it's working with.

Q: If a user needs to know their current identity for Zeev and Pydantic AI?

The getme tool pulls the user data. This information is validated, meaning if the API returns bad user info, your agent fails loudly instead of continuing with incorrect assumptions.

Q: What if I need to track a specific task in Zeev and Pydantic AI?

You get precise details about any single job using gettask. This validation layer ensures that every field describing the task is correct before your agent uses it.

Build reliable agents requiring strict type validation with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zeev MCP to Pydantic AI

Create your Vinkius account to connect Zeev 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 Zeev with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Start and manage process execution.

You start a new workflow using `create_request`. The agent passes necessary parameters, which are strictly validated against your defined models. It can then check the status or details of any instance by calling `get_request`.

Control task assignment and state changes.

When a job needs to move, you use `delegate_task`, ensuring the target user ID is correctly typed. To finalize work, your agent calls `finish_task`. You can also track pending jobs with `list_tasks`.

Audit and define process blueprints.

Before touching a live workflow, you confirm the rules by calling `get_process`, which validates the definition against your schema. If you need to stop something, `cancel_request` lets you terminate flows safely.

Setup guide

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

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

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

Use `get_request`. Since the response must pass through Pydantic validation, you'll get clean, type-safe data confirming the workflow's state.

The `list_processes` tool gives you the definitive list. Every process definition returned is validated, so your agent trusts the schema it's working with.

The `get_me` tool pulls the user data. This information is validated, meaning if the API returns bad user info, your agent fails loudly instead of continuing with incorrect assumptions.

You get precise details about any single job using `get_task`. This validation layer ensures that every field describing the task is correct before your agent uses it.

The server manages process definitions, request instances, and task records. By validating these three types of workflow data, you ensure structural integrity across all actions.

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