How to Use the Retable MCP in LlamaIndex

Q: How does LlamaIndex handle complex relational schemas in Retable?

The framework reads the schema using gettable to understand the column relationships before querying. This allows the agent to construct precise queries for listrecords without mapping columns manually.

Index live Retable spreadsheet data directly into your LlamaIndex vector stores for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Retable MCP to LlamaIndex

Create your Vinkius account to connect Retable to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Retable with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build search indexes from relational spreadsheets

This MCP Server provides `list_records` and `get_record` to let LlamaIndex ingest raw rows and convert them into searchable document nodes. Your query engine then searches across this relational data, matching user questions with actual spreadsheet values instead of guessing. You can schedule regular indexing jobs that pull fresh data from your sheets. The framework processes the output of `get_table` and updates your vector index, keeping your retrieval pipeline synced with your team's manual entries.

Ground LlamaIndex agent responses in real-time data

This MCP Server exposes `get_project` and `list_tables` to help your LlamaIndex agent locate the exact source of truth before answering user queries. This ensures that when a user asks about project status, the agent pulls the live record instead of relying on outdated training data. If the agent needs to verify its connection before running a heavy query, it runs `check_retable_status`. This prevents broken retrieval loops and ensures the underlying API is responsive before attempting to read large tables.

Write back RAG insights via Retable MCP Server tools

This MCP Server provides `create_record` and `update_record` to let LlamaIndex agents log user interactions directly back to your spreadsheet. This turns your relational database into an active memory layer for your RAG application. You can design workflows where the agent synthesizes information from a PDF, searches your vector store, and then updates a tracking row. This closes the loop between unstructured document reading and structured spreadsheet logging.

Setup guide

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

You use McpToolSpec to wrap the MCP Server tools and load your spreadsheet data into document nodes. From there, you can pass the records retrieved via `list_records` to a vector store index for semantic search.

Yes, your agent can query a vector index to find relevant context and then call `update_record` to modify the spreadsheet. This is useful for automated categorization or status tagging based on semantic content.

The framework reads the schema using `get_table` to understand the column relationships before querying. This allows the agent to construct precise queries for `list_records` without mapping columns manually.

Your agent can analyze retrieved documents for duplicates and use `delete_record` to clean up the spreadsheet. This lets you automate database hygiene using semantic comparison instead of strict keyword matching.

Your spreadsheet rows and table schemas are fetched over a secure, single-token connection managed by Vinkius. The raw records are only processed locally within your secure pipeline, ensuring your business metrics and tables are never leaked.

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