How to Use the Fig Finance MCP in LlamaIndex

Q: How do I expose Fig Finance tools to a LlamaIndex agent?

Initialize the BasicMCPClient with your Vinkius URL and wrap it in a LlamaIndex McpToolSpec to expose Fig Finance tools. You can then convert this spec to a tool list using totoollistasync and pass them directly to your LlamaIndex FunctionAgent.

Q: Can LlamaIndex index the transaction history retrieved from Fig Finance?

Yes, you can use LlamaIndex to fetch financial records via listtransactions and load them into a vector index. This allows your LlamaIndex agent to perform semantic search over past Fig Finance payments and customer financial behavior.

Q: How do I filter which Fig Finance tools my LlamaIndex agent can access?

Use the allowedtools filter when configuring your McpToolSpec in LlamaIndex to restrict access to Fig Finance endpoints. This ensures your LlamaIndex agent only has access to read tools like getloanstatus and cannot trigger write operations like disbursefunds.

Q: Does LlamaIndex support real-time balance checks with Fig Finance?

Yes, your LlamaIndex agent can call getbalance on demand during a query loop to get your current Fig Finance wallet status. This ensures your LlamaIndex RAG application always has the latest financial context before suggesting new loan applications.

Build RAG pipelines in LlamaIndex that index Fig Finance loan records and customer profiles for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fig Finance MCP to LlamaIndex

Create your Vinkius account to connect Fig Finance to LlamaIndex 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 Fig Finance with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Fig Finance customer profiles for LlamaIndex RAG

The `list_customers` tool retrieves your complete directory of borrowers from Fig Finance to build a searchable local index in LlamaIndex. LlamaIndex ingests these raw customer profiles, converts them into vector embeddings, and stores them in your vector database. When a user asks about a specific borrower's history, your LlamaIndex agent queries this vector store instead of making repetitive Fig Finance API calls. This approach combines static profile details with live data from `get_customer` to provide instant, context-rich answers.

Query real-time terms using LlamaIndex and MCP

The `get_loan_offers` tool pulls active lending rates and terms from Fig Finance directly into your LlamaIndex query engine. Your LlamaIndex agent evaluates these offers against historical transaction records retrieved by `list_transactions` to find the best match for the borrower. By indexing these Fig Finance financial transactions, you give your LlamaIndex agent the ability to detect spending patterns over time. These insights help your agent recommend specific Fig Finance loan structures during conversational RAG sessions with your clients.

Monitor Fig Finance repayment status in LlamaIndex

The `list_loans` tool generates a complete registry of your active Fig Finance portfolio for indexing within LlamaIndex. Your LlamaIndex agent parses this registry alongside `get_repayments` data to flag accounts that are falling behind on their schedules. This MCP integration allows you to build analytical LlamaIndex pipelines that trace credit risk trends across your entire Fig Finance portfolio. You can query the LlamaIndex index to find common factors among delinquent Fig Finance loans without manual spreadsheet analysis.

Setup guide

Set up Fig Finance MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Fig Finance MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Fig Finance tools.",
)
response = await agent.run("List recent Fig Finance data")

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 Fig Finance. 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 Fig Finance 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 Fig Finance MCP in LlamaIndex

Initialize the `BasicMCPClient` with your Vinkius URL and wrap it in a LlamaIndex `McpToolSpec` to expose Fig Finance tools. You can then convert this spec to a tool list using `to_tool_list_async` and pass them directly to your LlamaIndex `FunctionAgent`.

Yes, you can use LlamaIndex to fetch financial records via `list_transactions` and load them into a vector index. This allows your LlamaIndex agent to perform semantic search over past Fig Finance payments and customer financial behavior.

Use the `allowed_tools` filter when configuring your `McpToolSpec` in LlamaIndex to restrict access to Fig Finance endpoints. This ensures your LlamaIndex agent only has access to read tools like `get_loan_status` and cannot trigger write operations like `disburse_funds`.

Yes, your LlamaIndex agent can call `get_balance` on demand during a query loop to get your current Fig Finance wallet status. This ensures your LlamaIndex RAG application always has the latest financial context before suggesting new loan applications.

Every Fig Finance tool execution occurs within an ephemeral, zero-trust V8 isolate that destroys itself immediately after returning your customer records and transaction data to LlamaIndex. This architecture prevents any persistent storage of sensitive Fig Finance loan schedules or wallet balances outside your designated LlamaIndex environment.

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