How to Use the Fulcrum MCP in Pydantic AI

Q: How do I connect Pydantic AI to the Fulcrum MCP Server?

Just use the MCPToolset and give it your Vinkius endpoint URL. Pass the toolset into your Agent's constructor. Pydantic AI handles the tool discovery and response validation from the MCP server automatically.

Q: What happens if the Fulcrum API changes and the data no longer matches my Pydantic models?

Your agent will raise a ValidationError the moment it receives the mismatched data from a Fulcrum tool. This is a feature, not a bug. It prevents corrupted or unexpected data from propagating through your system and forces you to address the change.

Q: Is it better to use listfieldrecords or queryrecordssql with Fulcrum and Pydantic AI?

Use listfieldrecords when you need a list of full record objects that map cleanly to a Pydantic model. Use queryrecordssql for custom reports or aggregations where the output structure is unique. You'll just need to define a Pydantic model that matches the columns in your SQL SELECT statement.

Get validated, type-safe Fulcrum data in your agent. Pydantic AI ensures every API response matches your models, or it fails loudly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fulcrum MCP to Pydantic AI

Create your Vinkius account to connect Fulcrum 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 Fulcrum with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Data That Won't Break Your Code

This is the whole point of using Pydantic AI. When your agent calls a tool like `get_record_details` or `list_field_records`, the JSON response is automatically parsed and validated against a Pydantic model. If a field is missing or has the wrong type, you get an immediate `ValidationError`. No more silent failures or `KeyError` exceptions deep in your logic. You know the data structure is correct before your code even touches it. This makes your agent predictable and much easier to debug.

Dynamically Build UIs from Form Schemas

You can build some really solid workflows with this. Have your agent call `get_form_schema` to fetch the structure of any Fulcrum form. Since the response is a validated Pydantic model, you can trust it to programmatically generate a UI, a new data model, or even another agent. Imagine an agent that can adapt to form changes automatically. Someone adds a new field in Fulcrum, your agent calls `get_form_schema`, sees the change, and adjusts its own behavior without a redeploy. That's what type-safe, structured data gets you.

Write Correctness-First Fulcrum Agents

Combine Pydantic AI's validation with Fulcrum's powerful tools. Your agent can confidently run a `query_records_sql` command, knowing the result set will be checked for correctness. Or it can safely `create_record` because it built the payload based on a validated schema from `get_form_schema`. This MCP server is for developers who can't afford data corruption. If your agent is responsible for critical field data, you need to know that every API call and response is exactly what you expect. Pydantic AI enforces that contract.

Setup guide

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

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

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

Just use the `MCPToolset` and give it your Vinkius endpoint URL. Pass the toolset into your `Agent`'s constructor. Pydantic AI handles the tool discovery and response validation from the MCP server automatically.

Your agent will raise a `ValidationError` the moment it receives the mismatched data from a Fulcrum tool. This is a feature, not a bug. It prevents corrupted or unexpected data from propagating through your system and forces you to address the change.

Yes. Pydantic AI is model-agnostic. You can use this Fulcrum toolset with agents powered by OpenAI, Anthropic, Gemini, or any other supported LLM. The tool-calling and validation logic is completely separate from the model provider.

Use `list_field_records` when you need a list of full record objects that map cleanly to a Pydantic model. Use `query_records_sql` for custom reports or aggregations where the output structure is unique. You'll just need to define a Pydantic model that matches the columns in your SQL `SELECT` statement.

Your agent will be processing your field data records, form definitions, and member roles from Fulcrum. Security is handled at the transport layer; your Vinkius token authenticates every request over TLS. The server environment is stateless and ephemeral, meaning your data is never stored or logged after your request is complete.

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