How to Use the Sunsama MCP in Pydantic AI

Q: Can I delete tasks in Sunsama using the Pydantic AI framework?

Yes, deletetask is available. The model requires you to pass necessary identifiers and validates that the task exists before attempting deletion.

Q: How do I check user information or channels with Sunsama using Pydantic AI?

You use getuserprofile for personal data, and listchannels to see available communication groups. Both calls return structured, validated objects you can trust.

Guaranteed correctness when modifying Sunsama data with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sunsama MCP to Pydantic AI

Create your Vinkius account to connect Sunsama to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sunsama with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Update task details safely with `update_task`

When an existing task needs changes, the agent uses `update_task`. Because of runtime validation, you know exactly what data fields are being modified and if they match the expected schema. If your API returns unexpected format for the new text, the entire process fails loudly. You get a validation error—no silent corruption.

Get task details using `get_task_details`

Checking a specific task’s status with `get_task_details` returns data validated against Pydantic models. This means the output structure is guaranteed, regardless of what Sunsama reports. It's about correctness over speed here. You get typed Python objects representing the task details every time.

Manage tasks list and contexts with `list_tasks` or `list_contexts`

You can call `list_tasks` to pull all outstanding items, filtered by date, receiving a validated list. Similarly, getting available project structures using `list_contexts` provides reliable data. The agent ensures that the returned JSON structure for these lists adheres strictly to your defined Python models.

Setup guide

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

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

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

The framework validates every MCP response against strict Pydantic models at runtime. This means if the server sends unexpected data, your agent fails with a clear validation error instead of using bad info.

Yes, `delete_task` is available. The model requires you to pass necessary identifiers and validates that the task exists before attempting deletion.

You use `get_user_profile` for personal data, and `list_channels` to see available communication groups. Both calls return structured, validated objects you can trust.

The whole sequence stops immediately and throws a detailed validation error. You won't accidentally proceed with corrupted or incorrectly structured data from an intermediate tool call.

This MCP Server handles task details, user profiles, channels, contexts, and assignments. All these fields are strictly type-checked to guarantee your agent always receives predictable information.

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