How to Use the Cleared (ClearedIn) MCP in Pydantic AI

Get type-safe, validated access to your Cleared (ClearedIn) data in any Python agent with this MCP Server and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cleared (ClearedIn) MCP to Pydantic AI

Create your Vinkius account to connect Cleared (ClearedIn) 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 Cleared (ClearedIn) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Correct Data, Every Time

This isn't just about calling an MCP server; it's about trusting the data you get back. When your agent calls `get_verification_details`, Pydantic AI validates the entire response against a runtime model. You get exactly the data structure you expect. If the Cleared API ever changes a field name or data type, your code won't fail silently. Pydantic AI will raise a `ValidationError` immediately. It's a safety net that prevents data corruption from ever reaching your application logic.

Use Any LLM for Cleared Workflows

Pydantic AI doesn't lock you into a specific model provider. The same code you write to call `list_digital_signatures` can be powered by an OpenAI model, a Gemini model, or even a local model running on your own machine. This gives you the freedom to choose the right LLM for the job based on cost, performance, or privacy needs. You write the logic once, and Pydantic AI handles the model-specific integration.

A Modern MCP Server for Pydantic AI

This server is built to work with the latest Pydantic AI patterns. You'll use the unified `MCPToolset` class for setup, which is the current best practice. It's a cleaner, more direct way to connect your agent. Once connected, all the tools like `get_cleared_account_info` and `get_signature_details` are available to your agent. Pydantic AI ensures the JSON output from the MCP server is correctly parsed into type-safe Python objects you can work with.

Setup guide

Set up Cleared (ClearedIn) 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": {
        "cleared-clearedin-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Cleared (ClearedIn) 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 Cleared (ClearedIn). 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 Cleared (ClearedIn) 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 Cleared (ClearedIn) MCP in Pydantic AI

Pydantic AI will protect you. If the MCP server returns a new field or an unexpected data type, your agent will raise a `ValidationError` instead of processing bad data. You'll know immediately that something is wrong.

Yes. Pydantic AI is model-agnostic. You can configure it to use any compatible LLM, including open-source models you run yourself, while still getting all the type-safety benefits.

It takes the raw JSON from the server and parses it into a Pydantic model. This process automatically checks that every field exists and has the correct type (e.g., a string is a string, an integer is an integer), so you can trust the data in your code.

No, it's very direct. After the pip install, you just create an `MCPToolset` instance with your Vinkius server URL and add it to your agent's `toolsets` list.

This server accesses your account info and audit logs. Vinkius doesn't store any of it. Every transaction runs in a single-use, ephemeral container that self-destructs after sending you the response, and access is gated by your unique token.

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