How to Use the FynCom MCP in Pydantic AI

Q: Can I use the FynCom server with Pydantic AI and a local LLM?

Yes. Pydantic AI is model-agnostic. Connect the FynCom MCPToolset to an agent running any local model you want, and tools like sendreward and getwalletbalance will work without any changes.

Q: What happens if the FynCom API changes unexpectedly with Pydantic AI?

Your agent will raise a ValidationError and stop. This is a good thing. It prevents your application from breaking silently or, worse, processing incorrect data from a tool like listrewardhistory.

Q: How do I add the FynCom tools to my Pydantic AI agent?

It's straightforward. You create an MCPToolset with the FynCom server's URL and pass it to your agent's toolsets list. Pydantic AI automatically discovers the tools and creates typed Python functions for them.

Add type-safe, validated FynCom reward tools to your Pydantic AI agent and guarantee data correctness for every transaction.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FynCom MCP to Pydantic AI

Create your Vinkius account to connect FynCom 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 FynCom with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime Validated Rewards

This is why you use Pydantic AI. When your agent calls `get_campaign_details`, the JSON response is instantly parsed and validated against a Pydantic model. If the API ever returns a weird field or an incorrect data type, your code raises a `ValidationError`. No more silent failures. This means you can actually trust the data your agent operates on. It won't act on hallucinated API fields or corrupted information. When you call `send_reward`, you know the inputs are clean because they were validated on the way in.

Model-Agnostic MCP Server Integration

Pydantic AI doesn't care which LLM you use. You can run your agent with OpenAI, Gemini, or a local model on your own machine. The FynCom tools from this MCP server will work exactly the same. This frees you to swap out the brain of your agent without rewriting all your tool integrations. Your agent's ability to `list_reward_campaigns` or `add_reward_lead` is completely decoupled from the underlying language model.

Build Correct-by-Construction Workflows

Chain tools together with confidence. Because every input and output is typed, you can build workflows that are structurally sound. For instance, force the agent to successfully call `get_wallet_balance` and get a valid response before it's even allowed to attempt a `send_reward` call. You can build a sequence that calls `add_reward_lead` and then immediately uses another tool to verify the lead was created in your CRM. Pydantic's strictness ensures each link in the chain is solid.

Setup guide

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

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

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

It validates every single API response from the FynCom server at runtime. If data from `get_campaign_details` is malformed, your agent stops with a clear error instead of acting on bad info. It forces correctness.

Yes. Pydantic AI is model-agnostic. Connect the FynCom `MCPToolset` to an agent running any local model you want, and tools like `send_reward` and `get_wallet_balance` will work without any changes.

Your agent will raise a `ValidationError` and stop. This is a good thing. It prevents your application from breaking silently or, worse, processing incorrect data from a tool like `list_reward_history`.

It's straightforward. You create an `MCPToolset` with the FynCom server's URL and pass it to your agent's `toolsets` list. Pydantic AI automatically discovers the tools and creates typed Python functions for them.

Pydantic AI receives the JSON responses from the FynCom MCP server—things like campaign lists, wallet status, and transaction logs. It then parses that data into Pydantic models for validation inside your agent's local environment. The server itself only ever sees data relevant to the reward.

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