How to Use the Kintone MCP in LlamaIndex

Q: How do I integrate Kintone with LlamaIndex?

Install llama-index-tools-mcp via pip. Initialize a BasicMCPClient with your endpoint, create an McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex query specific Kintone records?

Yes. The agent uses the getrecord tool to fetch exact details for a single ID. It then incorporates those details directly into its synthesized response.

Q: How does the agent handle large data dumps?

You pass an optional query string to listrecords to filter the results at the API level. This keeps the token count manageable before the data hits your vector store.

Index your Kintone workspace into LlamaIndex to build searchable, data-grounded RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kintone MCP to LlamaIndex

Create your Vinkius account to connect Kintone 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 Kintone with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest Kintone App Data

This MCP Server allows your LlamaIndex application to pull live information from your custom databases using the `list_records` and `get_record` tools. The agent fetches the raw data and immediately processes it into a searchable vector store. You stop relying on static exports. When users query the system, the `FunctionAgent` checks the live app, retrieves the most recent entries, and grounds its answers in actual, up-to-the-minute business data.

Map App Structures Automatically

Understanding your database layout happens through the `list_apps` and `get_app_fields` tools. Your agent reads the configuration of your drag-and-drop forms to understand what fields exist before attempting to index them. This means you don't have to manually define schemas in your code. The agent discovers the structure on its own, ensuring that complex relational data gets chunked and embedded correctly for semantic search.

Write Back via MCP Server

Pushing new information back to your workspace requires the `add_records` and `update_records` tools. While LlamaIndex excels at reading and indexing, it can also execute these writing tools when a user requests a data correction. If a user identifies an outdated entry during a query, the agent can immediately trigger a fix. It formats the required JSON array and updates the target app without breaking the conversational flow.

Setup guide

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

Install `llama-index-tools-mcp` via pip. Initialize a `BasicMCPClient` with your endpoint, create an `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

Yes. The agent uses the `get_record` tool to fetch exact details for a single ID. It then incorporates those details directly into its synthesized response.

You can restrict which apps the agent accesses by applying an `allowed_tools` filter. This prevents the system from indexing sensitive spaces or irrelevant databases.

You pass an optional query string to `list_records` to filter the results at the API level. This keeps the token count manageable before the data hits your vector store.

The server transmits your workflow entries and form submissions directly to your LlamaIndex client. The zero-trust architecture ensures no intermediate caching occurs, keeping your proprietary business logic entirely within your own infrastructure.

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