How to Use the Franchimp MCP in Pydantic AI

Q: What's the best way to handle credits with Franchimp and Pydantic AI?

Before running a batch job, have your agent call listavailablecredits. Since Pydantic AI guarantees the response is a valid integer, you can safely check if credits > 0: without worrying about type errors or unexpected None values.

Q: What happens if the Franchimp API changes a field name?

Your Pydantic AI agent will fail loudly with a ValidationError. This is a feature, not a bug. It prevents your code from running with bad data and instantly tells you exactly what needs to be updated.

Get type-safe, validated franchise data in your Python agent. Pydantic AI ensures the Franchimp data you get is the data you expect.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Franchimp MCP to Pydantic AI

Create your Vinkius account to connect Franchimp 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 Franchimp with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Exception-Proof Data Pipelines

When your agent calls `get_franchisee_details` or `find_franchisee_by_email`, Pydantic AI automatically validates the response. If the API ever returned a malformed address or a missing phone number, your code would raise a `ValidationError` immediately. This means you can build data-cleaning pipelines with confidence. You don't have to write endless `if key in dict` checks. You just wrap the tool call in a try/except block and handle the rare validation error gracefully.

Trust Your Financial Numbers

The `get_investment_stats` tool returns critical financial data. With other frameworks, a change in the API could cause your agent to silently misinterpret a number, leading to bad analysis. Pydantic AI prevents this. It parses the response into a Pydantic model you define. If a field that should be an integer comes back as a string, the agent stops and tells you exactly what's wrong. No more silent data corruption.

Search Franchisors with Any LLM

Use the `search_franchisors` tool to find businesses matching your criteria. Because Pydantic AI is model-agnostic, you can run this with an OpenAI model, a local Llama, or a Gemini model without changing your tool-calling code. The toolset is completely decoupled from the LLM. This lets you swap out language models to find the best price/performance for your task, all while knowing the data returned from the Franchimp MCP server will be rigorously validated every time.

Setup guide

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

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

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

Pydantic AI validates every single response from the Franchimp MCP server against a strict schema. If a tool like `get_fdd_metadata` returns unexpected data, your agent will raise an error instead of using corrupted info. It forces correctness.

Yes. Pydantic AI is designed to be model-agnostic. You can connect it to the Franchimp tools and use it with any LLM that supports function calling, whether it's from OpenAI, Google, or running on your own machine.

Before running a batch job, have your agent call `list_available_credits`. Since Pydantic AI guarantees the response is a valid integer, you can safely check `if credits > 0:` without worrying about type errors or unexpected `None` values.

Your Pydantic AI agent will fail loudly with a `ValidationError`. This is a feature, not a bug. It prevents your code from running with bad data and instantly tells you exactly what needs to be updated.

The Franchimp server only processes the specific franchisor and franchisee data your agent requests. Your API calls are stateless. The Vinkius platform ensures each request runs in a clean, isolated environment that's destroyed after use, so none of your query data is ever persisted.

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