How to Use the LendAPI MCP in Pydantic AI

Q: How do I register the LendAPI MCP Server with my Pydantic AI agent?

Install pydantic-ai-slimmcp and instantiate MCPToolset with your Vinkius HTTP endpoint. Pass the toolset into your Agent constructor to give your model access to all eight loan management tools.

Q: Can I use getborrowerdetails from LendAPI to build type-safe profiles in Pydantic AI?

Yes. You can query getborrowerdetails and map the output directly into a custom Pydantic model, ensuring that every borrower field matches your strict data types.

Build type-safe underwriting agents with Pydantic AI to validate borrower profiles and loan applications at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LendAPI MCP to Pydantic AI

Create your Vinkius account to connect LendAPI 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 LendAPI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate borrower profiles before writing to LendAPI

The `create_new_borrower` tool registers applicant profiles directly into your database. By running this through your agent via our MCP connection, the framework validates all incoming fields against strict Pydantic models at runtime. If a borrower submits an invalid email format or a negative income figure, the system catches it instantly. Your agent fails loudly before making the API call, protecting your backend from corrupted profile schemas.

Submit credit files safely using this MCP Server

The `submit_loan_application` tool triggers the underwriting decision engine for a completed file. Your agent verifies that all required fields from the credit file match your internal models before executing the submission. This pre-flight validation prevents rejected API calls due to missing metadata. If the decision engine returns an unexpected state, the framework raises a validation error immediately so you can fix the schema mismatch.

Fetch verified picklists for Pydantic AI agents

The `get_lendapi_picklists` tool retrieves the active dropdown options and validation rules from your lending portal. Your agent uses these values to dynamically update its internal validation schemas during a session. This ensures your agent only generates applications that match current credit policy. It eliminates silent failures caused by outdated state codes, loan terms, or borrower classifications.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass the toolset into your `Agent` constructor to give your model access to all eight loan management tools.

The framework validates the API response against your model schemas at runtime. If the payload doesn't match, the agent raises a validation error immediately, preventing corrupt data from passing downstream.

Yes. You can query `get_borrower_details` and map the output directly into a custom Pydantic model, ensuring that every borrower field matches your strict data types.

Implement a local retry mechanism or limit your agent's execution steps. Since `list_loan_applications` is a bulk query, wrapping your agent's loops in standard Python backoff handlers prevents HTTP 429 errors.

Yes. Your credit applications, borrower profiles, and underwriting metadata are processed inside isolated, ephemeral V8 sandboxes. Vinkius encrypts your credentials and never stores your financial data.

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