How to Use the LendAPI MCP in OpenAI Agents SDK

Q: How do I connect the LendAPI MCP Server to my OpenAI Agents SDK project?

Install openai-agents and initialize MCPServerStreamableHttp using your Vinkius endpoint. Pass the server instance directly into your Agent's mcpservers list, and set cacheToolsList=True to minimize startup latency.

Q: Does the agent automatically know the correct fields for getborrowerdetails?

Yes, the server exposes the JSON schema for getborrowerdetails directly to the model. Your agent reads the required borrower ID from the conversation context and executes the query without hardcoded parameters.

Run production-ready credit underwriting agents using the OpenAI Agents SDK to manage borrower records and submit applications.

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 OpenAI Agents SDK

Create your Vinkius account to connect LendAPI to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build safe onboarding pipelines with OpenAI Agents SDK

The `create_new_borrower` tool registers new applicants directly into your underwriting system. Your agent handles the initial intake, validates the input structure, and writes the record to LendAPI without manual data entry. By mapping this to your agent's toolset, you prevent duplicate profiles. The OpenAI dashboard traces every parameter sent, ensuring your agent doesn't hallucinate SSNs or income figures during execution.

Execute underwriting decisions through this MCP Server

The `submit_loan_application` tool pushes completed credit files to the underwriting engine via this MCP tool. A specialized routing agent validates the application state before triggering this tool, preventing premature submissions. If the credit bureau pull returns an error, the agent catches the failure in the trace log. You can hand off the session to a human reviewer or a secondary agent tasked with checking `get_application_details` for specific rejection codes.

Fetch real-time picklists for flawless schema compliance

The `get_lendapi_picklists` tool provides the exact metadata fields and valid loan options currently active in your lending portal. Your agent queries this tool first to map incoming user responses to valid API values. This pre-validation step means your OpenAI Agents SDK pipeline rejects bad data before it ever hits your database. It eliminates API submission failures caused by outdated state codes or invalid loan terms.

Setup guide

Set up LendAPI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LendAPI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LendAPI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LendAPI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LendAPI Agent",
            instructions="You have access to LendAPI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and initialize `MCPServerStreamableHttp` using your Vinkius endpoint. Pass the server instance directly into your Agent's `mcp_servers` list, and set `cacheToolsList=True` to minimize startup latency.

Yes. You can set strict system instructions or use agent handoffs so only a designated underwriting agent can invoke `create_loan_application`. This prevents general conversational agents from accidentally generating drafts.

Limit your agent's loop execution or implement a local queue. Since `list_loan_applications` returns paginated records, your agent should process batches sequentially rather than firing concurrent requests.

Yes, the server exposes the JSON schema for `get_borrower_details` directly to the model. Your agent reads the required borrower ID from the conversation context and executes the query without hardcoded parameters.

All borrower profiles and application payloads pass through an ephemeral, zero-trust Vinkius V8 sandbox. No database records are stored on our servers, and your API credentials remain encrypted in transit.

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