How to Use the ClickTime MCP in Pydantic AI

Add type-safe, validated ClickTime tools to your Pydantic AI agent for guaranteed data correctness.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClickTime MCP to Pydantic AI

Create your Vinkius account to connect ClickTime 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 ClickTime with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Schema-Validated ClickTime Data

This server gives your agent direct access to ClickTime data like projects, users, and time entries. Your Pydantic AI agent doesn't just get a JSON blob; it gets a Pydantic model instance. Every response is automatically parsed and validated. If ClickTime ever changes its API or returns an unexpected field, your agent won't silently fail or hallucinate. It will raise a `ValidationError` immediately. This means you can trust the data from tools like `list_clicktime_projects` and `get_my_clicktime_profile` without writing any validation code yourself.

Build Reliable Financial Automation

Automate billing and payroll with confidence. Your agent can call `get_high_volume_time_report` to pull up to 2500 time entries. Pydantic AI ensures every single entry conforms to your expected schema before your code ever touches it. This strictness is what you want for financial data. There's no room for error when you're calculating hours or invoicing clients. By using this MCP server with Pydantic AI, you're building a system that prioritizes correctness above all else.

A Model-Agnostic ClickTime MCP Server

Pydantic AI doesn't lock you into a specific LLM. You can use this ClickTime toolset with OpenAI, Anthropic, Gemini, or even a local model. The tools—`list_clicktime_clients`, `list_clicktime_jobs`, `list_clicktime_tasks`—work the same way everywhere. The setup is simple: `pip install "pydantic-ai-slim[mcp]"` and then point the `MCPToolset` at your Vinkius server URL. The framework handles the rest, giving you a reliable, model-agnostic way to interact with your ClickTime account.

Setup guide

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

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

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

Pydantic AI automatically validates every response from our ClickTime MCP Server against a Pydantic model. If a field is missing, has the wrong type, or is unexpected, your agent will immediately raise a validation error instead of processing bad data.

It's quick. After installing the library with the MCP extra, you create an instance of `MCPToolset` and give it your Vinkius URL for the ClickTime server. Then you just add that toolset to your agent's `toolsets` list.

Yes. Pydantic AI is model-agnostic, so you can pair our ClickTime MCP Server with any compatible local or proprietary LLM. The tool-calling and validation logic works independently of the model you choose.

Our server is designed to work with the latest Pydantic AI library that supports the unified `MCPToolset`. We manage the connection to the ClickTime API, so you don't have to worry about upstream API changes breaking your agent.

All requests for your ClickTime data, such as task lists or user profiles, are routed through a dedicated Vinkius server instance that's destroyed after use. The connection is secured by your private token, and the Pydantic AI library simply receives the data over a secure channel. No sensitive data is logged or stored on our servers.

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