How to Use the Mosaic (Resource Planning & Workforce Management) MCP in Pydantic AI

Q: Is it hard to set up?

No, it's very direct. You install the library, create an MCPToolset with the server URL, and pass it to your agent's constructor. There's no need to manually define the tools or their schemas; Pydantic AI handles that.

Get type-safe, validated access to your Mosaic data. Build correct-by-construction agents with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mosaic (Resource Planning & Workforce Management) MCP to Pydantic AI

Create your Vinkius account to connect Mosaic (Resource Planning & Workforce Management) 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 Mosaic (Resource Planning & Workforce Management) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Data, Every Time

Tools like `list_projects` and `list_budgets` are automatically validated when used with Pydantic AI. When your agent calls a tool, Pydantic AI checks the response against a strict schema, raising a `ValidationError` instantly if the data is malformed. This means no silent data corruption. Your agent won't hallucinate a project's budget or misinterpret a work plan from `list_work_plans`. If the data isn't exactly what's expected, your application stops—which is what you want for financial and resource planning.

Your Agent, Your LLM

This Mosaic toolset works with any LLM you connect to Pydantic AI, whether it's OpenAI, Anthropic, or a local model. Tools like `list_work_plans` and `list_members` will work the same way everywhere, so you're not locked into a single provider. This lets you choose the right model for the job. Use a fast model for simple lookups like `get_member`, and a more powerful one for complex analysis that combines `list_cost_rates` and `list_budgets`. The MCP integration logic doesn't change.

A Reliable MCP Server for Pydantic AI

This MCP Server provides 12 structured tools for your Pydantic AI agent to query Mosaic. It's not a raw API wrapper; it's a set of defined operations that your agent can reason about and use to answer questions about your resources and projects. Setup is straightforward. Just instantiate the `MCPToolset` with the Vinkius URL and add it to your agent. Pydantic AI handles the HTTP calls and, most importantly, the response validation provided by this MCP, so you can focus on building the agent's logic.

Setup guide

Set up Mosaic (Resource Planning & Workforce Management) 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": {
        "mosaic-resource-planning-workforce-management-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Mosaic (Resource Planning & Workforce Management) tools.",
)

result = await agent.run("List recent Mosaic (Resource Planning & Workforce Management) 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 Mosaic. 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 Mosaic (Resource Planning & Workforce Management) 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 Mosaic (Resource Planning & Workforce Management) MCP in Pydantic AI

Correctness. Pydantic AI validates every piece of data coming from the Mosaic tools against a schema. If an API response changes unexpectedly, you get an immediate error instead of letting bad data flow into your agent's logic.

Yes. Pydantic AI is model-agnostic. You can connect the Mosaic toolset to an agent powered by a local model just as easily as one using a major cloud provider. The tools like `list_projects` and `list_work_plans` will function identically.

It's all about runtime validation. When your agent decides to call `list_budgets`, Pydantic AI ensures the response is a valid list of budget objects. This prevents your agent from making decisions based on incomplete or incorrect financial data.

No, it's very direct. You install the library, create an `MCPToolset` with the server URL, and pass it to your agent's constructor. There's no need to manually define the tools or their schemas; Pydantic AI handles that.

The server has read-only access to your Mosaic workforce data, like work plans, project details, and cost rates. Vinkius isolates each request in an ephemeral sandbox with a unique auth token. Pydantic AI adds its own security benefit by strictly validating the data schema, which helps prevent data leakage from malformed API responses.

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