How to Use the Kintone MCP in CrewAI

Q: How do I assign specific Kintone tools to different agents in CrewAI?

When defining your Agent in CrewAI, use the toolfilter argument in the MCPServerHTTP configuration. This lets you expose only listrecords to a "Researcher" agent and only updaterecords to an "Executor" agent, for example.

Q: Can a CrewAI agent delete records from Kintone?

Yes, if you give it access to the deleterecords tool. You should be careful with this. It's best to assign this tool only to a highly specialized agent and build a confirmation step into your crew's process.

Deploy autonomous agent crews to manage your Kintone environment. Let CrewAI agents monitor, update, and organize your business apps.

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 CrewAI

Create your Vinkius account to connect Kintone to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Kintone Data Curation

Assign one agent the role of "Analyst." Its job is to periodically run `list_records` on a specific Kintone app to find incomplete or outdated entries. It then passes those record IDs to a second "Updater" agent. The Updater agent takes the list, uses `get_record` to fetch the full data for each, and then calls `update_records` to standardize fields or flag them for review. This is how you use a crew to automate data hygiene.

Build a Kintone Monitoring Crew

You can create a crew dedicated to watching your Kintone spaces. An "Observer" agent could use `get_space_details` to check for new members in key collaboration spaces. A "Reporter" agent could then take that information and use `add_records` to log the changes in a central audit app. This moves beyond simple scripts. With CrewAI, you're building a system of roles and responsibilities. The agents collaborate using their shared memory, passing context and tasks between them to manage your Kintone setup autonomously.

Run Autonomous App Audits with CrewAI

Set up a "Governance" crew. The first agent's task is to run `list_apps` to get a complete inventory of every app in your Kintone domain. It passes this list to a "Schema Inspector" agent. The Inspector agent iterates through the list, calling `get_app_fields` on each one to check for compliance with your company's data standards. If it finds a problem, it can delegate to a "Janitor" agent to perform a cleanup or to a "Notifier" agent that logs the issue using `add_records`.

Setup guide

Set up Kintone MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kintone tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kintone Analyst",
    goal="Access and analyze Kintone data via MCP.",
    backstory="Expert analyst with direct Kintone access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kintone transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Kintone Analyst",
        goal="Access and analyze Kintone data via MCP.",
        backstory="Expert analyst with direct Kintone access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kintone transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

When defining your Agent in CrewAI, use the `tool_filter` argument in the `MCPServerHTTP` configuration. This lets you expose only `list_records` to a "Researcher" agent and only `update_records` to an "Executor" agent, for example.

Yes, if you give it access to the `delete_records` tool. You should be careful with this. It's best to assign this tool only to a highly specialized agent and build a confirmation step into your crew's process.

A "Researcher" agent would gather the data. A "Transformer" agent would format it into the correct JSON structure for Kintone. Finally, a "Loader" agent would take the formatted data and execute the `add_records` tool to insert it.

CrewAI's process management determines the next step. Depending on your setup, the task might be retried, passed to a different agent, or halt the crew's execution. The MCP server itself is stateless and just reports success or failure.

Your CrewAI agents interact with Kintone through this MCP server, not directly. The server touches only the data required for a given tool—like records from `list_records` or app structures from `get_app_fields`. All operations occur within a sandboxed, single-use environment that doesn't persist data.

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