How to Use the Fee Navigator MCP in Pydantic AI

Type-safe merchant auditing with Pydantic AI. Use Fee Navigator to get validated financial insights in your Python agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fee Navigator MCP to Pydantic AI

Create your Vinkius account to connect Fee Navigator 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 Fee Navigator with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict types in Pydantic AI

Every tool call from `get_proposal` or `get_merchant` is validated against Pydantic models at runtime. If the API returns a malformed field, your agent stops immediately. This keeps your audit logic clean. You don't have to worry about silent failures or unexpected data types creeping into your financial reports.

Analyze statements with Pydantic AI safety

Pass your statement files through `upload_statement` and trust that the output matches your expected schema. The server handles the heavy lifting of PDF parsing while Pydantic AI manages the validation. If the data doesn't fit the model, you get a clear error. This makes debugging your merchant analysis pipelines straightforward and fast.

Query benchmarks using Fee Navigator tools

Use `get_industry_stats` to pull market data into your agent. Because you are using Pydantic AI, you can define your own response models to cast this data into your preferred format. It ensures that the savings projections your agent generates are always formatted correctly. Your final proposals remain consistent across every client audit.

Setup guide

Set up Fee Navigator 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": {
        "fee-navigator-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim MCP package and use the MCPToolset class. Pass your server URL to the toolset and add it to your agent's list of tools. It handles both SSE and HTTP transports for your connection.

Yes. The framework validates every piece of data returned by the server. If the structure deviates from your model, the agent throws a validation error instead of hallucinating values.

You can. The combination of type-safe responses and server-side analysis makes this a reliable stack for auditing merchant statements. It prioritizes correctness over raw speed.

Vinkius handles the token injection. You provide the endpoint, and the server performs the authentication. Your agent code stays clean and doesn't need to manage secrets.

The server operates in a sandboxed, ephemeral environment. It only touches the merchant statement binary to extract fees. No statement data is persisted or shared after the tool execution completes.

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