Can I stop a running timer through the agent?

Yes! Use the `stop_current_timer` tool. Provide your workspace and user ID, and the agent will instruct Clockify to stop the active timer immediately.

How do I see the projects for a specific workspace?

Use the `list_workspace_projects` tool with the workspace ID. Your agent will fetch all projects, allowing you to see which ones are billable and their associated clients.

Where do I find my Clockify API Key?

Log in to Clockify, go to **Settings**, and select **My Profile**. Scroll to the bottom to find and generate your API Key.

Clockify MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Clockify
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Clockify through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Clockify "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Clockify?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Clockify MCP Server

Connect your Clockify account to any AI agent and take full control of your time tracking and project management through natural conversation. Streamline how you monitor work hours and team productivity natively.

Pydantic AI validates every Clockify tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Workspace Oversight — List and retrieve details for all workspaces you have access to natively
Project Intelligence — Access and monitor all projects and clients configured in your account flawlessly
Time Tracking — List and retrieve details for all time entries for any user in your team securely
Timer Management — Start and stop timers directly from your chat interface to ensure accurate logging flawlessly
Team Logistics — List all users and team members within a workspace to understand allocation securely
Productivity Auditing — Retrieve detailed time entry metadata including descriptions and project associations flawlessly

The Clockify MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Clockify to Pydantic AI via MCP

Follow these steps to integrate the Clockify MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Clockify with type-safe schemas

Why Use Pydantic AI with the Clockify MCP Server

Pydantic AI provides unique advantages when paired with Clockify through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Clockify integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Clockify connection logic from agent behavior for testable, maintainable code

Clockify + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Clockify MCP Server delivers measurable value.

Type-safe data pipelines: query Clockify with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Clockify tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Clockify and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Clockify responses and write comprehensive agent tests

Clockify MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Clockify to Pydantic AI via MCP:

add_new_time_entry

Add a new time entry to a workspace

get_my_clockify_profile

Retrieve information about the authenticated user

list_clockify_workspaces

List all workspaces the user has access to

list_user_time_entries

List time entries for a specific user in a workspace

list_workspace_clients

List all clients configured in a workspace

list_workspace_projects

List all projects within a specific workspace

list_workspace_users

List all users within a specific workspace

stop_current_timer

Stop the currently running timer for a specific user

Example Prompts for Clockify in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Clockify immediately.

"List all my Clockify workspaces."

"Show me the last 5 time entries for user 'John Doe'."

"Stop my running timer in the 'Engineering' workspace."

Troubleshooting Clockify MCP Server with Pydantic AI

Common issues when connecting Clockify to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Clockify + Pydantic AI FAQ

Common questions about integrating Clockify MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Clockify MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.