How to Use the Height (Project Management) MCP in Pydantic AI

Q: Is this MCP Server read-only?

Yes. The tools provided are for reading data only, such as listtasks and listactivities. This focus on data retrieval makes it a perfect fit for Pydantic AI, where the primary goal is often ensuring the integrity of data being ingested by an application.

Get type-safe, validated data from your Height workspace with Pydantic AI. Build agents that never fail silently on bad API responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Height (Project Management) MCP to Pydantic AI

Create your Vinkius account to connect Height (Project Management) 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 Height (Project Management) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarantee Correctness with Pydantic Models

Every tool in this MCP server returns data that is automatically validated against a Pydantic model. When your agent calls `get_task`, you don't get a blob of JSON. You get a clean, typed object or a loud, immediate validation error. This means your agent's logic is built on a foundation of correctness. If the Height API ever changes or returns something unexpected, your agent stops instead of processing corrupted data. No more silent failures or bizarre downstream bugs.

Build Reliable, Model-Agnostic Auditors

Use any LLM you want—OpenAI, Anthropic, a local model—your Pydantic AI agent doesn't care. The Pydantic AI framework handles the tool-calling logic. Your job is to define what to do with the validated data from tools like `list_tasks` and `list_activities`. This is perfect for building reliable auditing and reporting agents. You can create an agent that cross-references `list_users` with task assignments from `list_tasks`, knowing the data structures will always be consistent, regardless of the LLM driving the process.

Focus on Logic, Not Data Cleaning

Since Pydantic AI and the MCP server handle data validation, you can stop writing defensive code and boilerplate data-cleaning functions. The data you get from `list_lists` or `workspace` is ready to use the moment you get it. This lets you focus on the actual business logic of your agent. Spend your time figuring out what insights to draw from the data, not writing `try/except` blocks to handle a missing key or an incorrect data type. It just works.

Setup guide

Set up Height (Project Management) 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": {
        "height-project-management-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Height (Project Management) 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 Height. 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 Height (Project Management) 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 Height (Project Management) MCP in Pydantic AI

Pydantic AI automatically validates the raw JSON response from tools like `get_task` against a corresponding Pydantic model. If the data doesn't match the expected structure—for example, a field is missing or the wrong type—it raises a `ValidationError` immediately.

Yes. Pydantic AI is model-agnostic. You can configure it to work with local models running via Ollama or llama.cpp, as well as major commercial APIs. The Height toolset will function the same way.

Your agent will fail loudly and immediately with a descriptive error. Instead of your code breaking in a weird way later on, Pydantic's validation catches the mismatch between the API response and your data model right at the source.

Yes. The tools provided are for reading data only, such as `list_tasks` and `list_activities`. This focus on data retrieval makes it a perfect fit for Pydantic AI, where the primary goal is often ensuring the integrity of data being ingested by an application.

The server accesses your workspace metadata, task details, user lists, and project activity logs from Height. Security starts at the data layer; Pydantic's runtime validation ensures that no malformed data even enters your agent's logic. This is layered on top of Vinkius's single-tenant, ephemeral sandboxes for each MCP server instance.

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