How to Use the LiquidPlanner Classic MCP in Pydantic AI

Q: Can I run type-safe task updates in LiquidPlanner Classic using Pydantic AI?

Yes. When your agent calls updatetask, Pydantic AI validates the payload schema at runtime, ensuring all LiquidPlanner Classic task edits match the expected API structure exactly.

Build type-safe project management pipelines in Pydantic AI that validate LiquidPlanner Classic data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiquidPlanner Classic MCP to Pydantic AI

Create your Vinkius account to connect LiquidPlanner Classic 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 LiquidPlanner Classic with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime type safety with Pydantic AI

LLMs love to hallucinate fields when generating JSON payloads for project management. Pydantic AI forces every response from `get_task` and `get_project` through strict Pydantic schemas, raising immediate validation errors if the LiquidPlanner Classic data is corrupt. This prevents malformed data from ever hitting your LiquidPlanner Classic database. If the model tries to write an invalid date format to `update_task`, the Pydantic AI framework stops the execution before the API call even occurs.

Model-agnostic scheduling pipelines

Do not lock yourself into a single model provider for managing your LiquidPlanner Classic workspaces. Pydantic AI lets you run this MCP Server with OpenAI, Anthropic, or local models while maintaining the exact same validation rules for `create_task` and `list_tasks`. You can swap models in your Pydantic AI configuration file without rewriting your LiquidPlanner Classic tool calls. The framework ensures that whether you are listing workspaces with `list_workspaces` or checking team rosters with `list_members`, the output structure remains identical.

Clean error boundaries for task creation

When building complex LiquidPlanner Classic project structures, nested tasks can easily fail if a parent ID is missing. Using `create_task` with Pydantic AI guarantees that your agent validates the parent ID parameter before making the network request. If the Pydantic AI agent fails to provide a required field for `create_project`, the framework throws a clear Python exception. You can catch these exceptions in your application logic to gracefully prompt the agent for the missing LiquidPlanner Classic information.

Setup guide

Set up LiquidPlanner Classic 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": {
        "liquidplanner-classic-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the package with the MCP library, then instantiate the MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly into your Pydantic AI Agent's toolsets list to manage your LiquidPlanner Classic workspaces.

The Pydantic AI framework will immediately raise a validation error. This prevents your agent from processing corrupt project or task data and ensures strict type safety across your LiquidPlanner Classic pipeline.

Yes. When your agent calls `update_task`, Pydantic AI validates the payload schema at runtime, ensuring all LiquidPlanner Classic task edits match the expected API structure exactly.

Yes, Pydantic AI is completely model-agnostic. You can connect this toolset to local models or enterprise APIs to manage your LiquidPlanner Classic projects with `list_projects` and `get_workspace`.

All LiquidPlanner Classic task assignments, project structures, and scheduling timelines are processed in ephemeral memory. Your credentials and project data are never cached or logged outside your active Pydantic AI session.

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