How to Use the LiftedWork MCP in Pydantic AI

Run type-safe candidate matching and task tracking with Pydantic AI validation using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiftedWork MCP to Pydantic AI

Create your Vinkius account to connect LiftedWork 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 LiftedWork with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe task creation with Pydantic AI validation

The `create_task` tool takes a JSON string that your agent validates against your Pydantic models before hitting the database. This stops malformed task data or missing fields from breaking your recruitment tracking. When starting new hiring initiatives, the `create_project` tool sets up a clean workspace. Because your code enforces strict validation, you never have to worry about silent database corruption.

Strict type checks on client and project lists

The `list_clients` tool fetches active client directories and validates them at runtime. If a client record contains unexpected nulls, the agent fails loud and fast to protect your database integrity. To map out active work, the `list_projects` tool pulls your current project list. The framework checks that every field matches your schema, blocking hallucinated data from slipping through.

Audit timesheets using this MCP Server

The `list_time_entries` tool exposes raw hours logged by your contract staff. Running this through a typed schema lets your agent calculate billing figures with complete accuracy. Finally, the `list_tasks` tool lets you inspect the exact state of your agency pipeline. It provides the structured foundation your agent needs to build type-safe reports on hiring bottlenecks.

Setup guide

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

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

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

Use the unified MCPToolset class pointing to your HTTP endpoint. Pass the toolset instance to your agent's toolsets argument, and the framework will automatically handle the schema mapping.

The framework will throw a validation error at runtime. This prevents your agent from processing corrupt client lists or malformed time entries, keeping your pipeline secure.

Pydantic AI handles async calls natively. The underlying MCP HTTP connection manages async requests, allowing your agent to run `list_tasks` and `list_projects` in parallel without blocking.

Yes. Pydantic AI is model-agnostic, meaning you can run the LiftedWork tools with local models, Anthropic, or Gemini while maintaining strict type validation.

All transaction data, including active tasks and client directories, passes through secure, isolated sandboxes. We enforce zero-trust access controls, ensuring that your operational agency data is never exposed to external networks.

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