How to Use the Mercury MCP in LlamaIndex

Q: Can Mercury tools be filtered in LlamaIndex?

Absolutely, you can pass an allowedtools list to the agent constructor. This ensures the agent only has access to the functions you explicitly permit.

Index your Mercury financial history into LlamaIndex for semantic search and retrieval.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to LlamaIndex

Create your Vinkius account to connect Mercury 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 Mercury with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Mercury data for LlamaIndex

Convert your transaction history into a searchable vector store. By running `list_transactions` and indexing the results, your agent gains a historical context that stays grounded in reality. Stop relying on the agent's memory. Instead, query the index to get precise answers about past payments and account movements.

Ground AI answers with live bank data

Use the agent to look up specific entries via `get_transaction` and then store that information in your knowledge base. This creates a feedback loop where API data informs future agent decisions. Your agent doesn't just guess facts. It retrieves them from the indexed bank data, ensuring every response is backed by actual account records.

Create RAG pipelines with bank records

Combine your internal documents with live banking data in one unified index. This allows your agent to answer questions by comparing policy documents against current `get_treasury_balance` figures. The integration handles the mapping between your tools and the vector store. You control what data gets indexed and how the agent accesses it.

Setup guide

Set up Mercury 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 Mercury 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 Mercury tools.",
)
response = await agent.run("List recent Mercury 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 Mercury. 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 Mercury 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 Mercury MCP in LlamaIndex

It uses the MCP client to fetch data, then processes the output for indexing. You can set up a tool spec to automate this ingestion.

Absolutely, you can pass an allowed_tools list to the agent constructor. This ensures the agent only has access to the functions you explicitly permit.

The index is stored locally or in your designated vector store. You control the access layer, keeping your financial data within your infrastructure.

You can trigger re-indexing whenever you need fresh data. Simply call the tool again and update the vector store with the new output.

The server uses a single endpoint token for authentication. Your data resides only in your authorized environment, ensuring no third party sees your transaction details.

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