How to Use the Float MCP in Pydantic AI

Q: How do I register the Float toolset in Pydantic AI?

Use the MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset directly into your Agent constructor to give your model access to listprojects.

Q: Can I use Pydantic AI to track logged hours in Float?

Yes, the agent can call getloggedtime to fetch tracked hours. Pydantic validates the returned time metrics against your defined Python models.

Get type-safe resource scheduling with Pydantic AI to guarantee valid Float database writes every single time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Float MCP to Pydantic AI

Create your Vinkius account to connect Float 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 Float with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate allocation writes with Pydantic AI

`create_allocation` executes schedule changes only after validating the payload schema at runtime. If your agent tries to write a bad date format, the system halts before making the API call. This type-safety prevents corrupted calendars and broken resource blocks when calling the MCP Server. Pydantic AI guarantees that every written record matches the exact structure your database expects.

Fetch team details without data corruption

`get_person` returns clean, typed Python objects containing employee roles, emails, and department codes. Your agent can immediately use these fields without manual parsing or casting. If the API payload changes, your code triggers a validation error immediately. This loud failure mode protects downstream scheduling logic from silent data errors.

Read project task labels using this MCP Server

`list_project_task_names` lists the active task tags like design, dev, or copy writing. Your agent reads these labels to assign the right type of work to the right person. Because this MCP Server integrates with Pydantic AI's model-agnostic layer, you can swap your LLM provider without rewriting your validation schemas. The task list always returns structured, predictable data.

Setup guide

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

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

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

Use the `MCPToolset` class with your Vinkius HTTP endpoint. Pass this toolset directly into your `Agent` constructor to give your model access to `list_projects`.

Pydantic AI raises a validation error at runtime. This prevents your agent from processing malformed data when executing tools like `list_allocations`.

No, Vinkius hosts the server externally. Your Pydantic AI agent connects to the managed endpoint over a secure HTTP or SSE transport layer.

Yes, the agent can call `get_logged_time` to fetch tracked hours. Pydantic validates the returned time metrics against your defined Python models.

Your team's allocation records, task lists, and logged hours are transmitted over encrypted TLS. Vinkius handles the API handshake ephemerally, so no scheduling records are saved on our infrastructure.

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