How to Use the DeskTime MCP in Pydantic AI

Q: Can I delete records using DeskTime and Pydantic AI?

Your agent can trigger removeproject to delete workspaces. Because of the strict typing, it will only execute if the project ID strictly matches your schema requirements.

Bring type-safe DeskTime integrations to Pydantic AI. Validate every time log and productivity score at runtime to prevent silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeskTime MCP to Pydantic AI

Create your Vinkius account to connect DeskTime 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 DeskTime with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate DeskTime MCP Server Data

Time tracking data dictates payroll, so accuracy matters more than speed. When your agent calls `get_productivity_reports` through this MCP Server, Pydantic AI validates the exact structure of the response. If the API changes or returns unexpected fields, the agent fails loudly. Hallucinated metrics are impossible here. The framework ensures that outputs from `get_employee_performance` match your predefined Python models perfectly. You never have to worry about the LLM inventing fake hours for your staff.

Manage Projects with Strict Typing

Setting up new client work requires precise inputs. Your agent executes `create_project` and `create_new_task` using validated parameters. The system rejects malformed requests before they even reach the Vinkius endpoint. Auditing existing work is just as reliable. The agent fetches `list_projects`, followed by `get_project_details`, to build a typed hierarchy of active jobs. It can then safely run `mark_task_completed` because the task IDs are guaranteed to be valid integers or strings.

Audit Employee Rosters Safely

Keeping your team directory synchronized requires pulling live data. The agent runs `list_employees` to get the master list, then checks `list_online_staff` to see who is currently active. Pydantic models catch any missing user IDs instantly. You can also pull `get_company_info` to verify global settings. Since Pydantic AI is model-agnostic, you can swap between Claude, OpenAI, or a local model without rewriting your MCP integration logic.

Setup guide

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

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

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

Install the slim package with MCP support. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass that toolset directly to your Agent instance.

Yes, it validates the inputs and outputs of every tool call. If `list_project_tasks` returns a string where a float was expected, the framework throws a runtime validation error.

Your agent can trigger `remove_project` to delete workspaces. Because of the strict typing, it will only execute if the project ID strictly matches your schema requirements.

Standard SDKs often silently ignore malformed JSON from external APIs. This framework guarantees that your agent only processes perfectly structured time logs and project details.

The tools expose raw project costs and individual employee tracking logs. Vinkius secures this pipeline by running the execution in an isolated V8 sandbox. Authentication is handled at the network edge, meaning your agent only sees the exact data it requested.

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