How to Use the Sally MCP in Pydantic AI

Q: How do I implement Sally in my Pydantic AI agent?

Install the slim package and use MCPToolset to connect your server. Pass the toolset to your agent to get immediate, type-safe access to all 12 tools.

Use Pydantic AI with Sally to enforce type-safe frontline workflows. Validate every task update and project record at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sally MCP to Pydantic AI

Create your Vinkius account to connect Sally 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 Sally with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe task operations for Pydantic AI

Every response from `get_task` or `list_tasks` is validated against your Pydantic models. If the data format shifts, your agent catches it immediately. This ensures your frontline data remains consistent. You avoid the silent failures that usually plague automated task management systems.

Reliable Sally MCP Server integration

Build your agent with the confidence that `update_task` and `create_task` behave predictably. The server provides strictly typed data structures for every interaction. Your agent handles errors gracefully when it encounters unexpected input. This keeps your production systems running without manual debugging.

Project and timesheet validation for Pydantic AI

Fetch project details with `get_project` and verify the integrity of the data before your agent processes it. It eliminates hallucinated fields and ensures accuracy. `get_timesheet_report` results are validated on arrival. You get clean, ready-to-use data for your reporting logic every single time.

Setup guide

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

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

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

Install the slim package and use `MCPToolset` to connect your server. Pass the toolset to your agent to get immediate, type-safe access to all 12 tools.

It does. If the API returns a shape that doesn't match your Pydantic model, the agent throws a validation error. You get a clear log of exactly what failed.

Absolutely. Since the server operates via standard protocols, it works with any model you choose, including local ones. Your agent logic remains the same.

You can. The server supports both Streamable HTTP and SSE, giving you flexibility in how your agent connects to the platform.

The server enforces strict runtime validation for your profile information. Only authenticated requests can reach the `get_profile` tool, keeping your personal workspace details private.

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