How to Use the Kong Gateway MCP in CrewAI

Q: How does CrewAI handle errors during Kong Gateway mutations?

If a tool call like createplugin fails due to a schema error or duplicate entry, the agent receives the error details. The agent then analyzes the issue, modifies its input parameters, and retries the operation automatically.

Run your Kong Gateway configuration dynamically using a collaborative team of agents with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kong Gateway MCP to CrewAI

Create your Vinkius account to connect Kong Gateway 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 Kong Gateway with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent gateway monitoring and tuning with CrewAI

The `get_status` and `list_plugins` tools allow your crew of specialized agents to audit your gateway setup. One agent can analyze traffic trends while another checks which plugins are active on high-traffic routes. This collaborative approach ensures that your gateway configuration matches your operational needs. The agents share context and coordinate actions, identifying misconfigured routes and applying fixes without human intervention.

Autonomous route and service provisioning

The `create_service` and `create_route` tools are exposed by this MCP server to onboarding agents. When a new service is deployed, the agent automatically configures the upstream mapping and routing rules. You do not need to write manual template scripts or run slow deployment pipelines. The CrewAI framework allows the agent to execute these configurations sequentially, verifying the setup at each step.

Security hardening via CrewAI agents

The `create_plugin` and `list_consumers` tools on this MCP server let your security agent audit access controls across your APIs. The agent scans for consumers without active plugins and applies key-auth or rate-limiting policies where needed. This proactive monitoring keeps your gateway compliant with security policies. The agent identifies gaps in your setup, reports them to the team, and applies the necessary plugins to secure vulnerable endpoints.

Setup guide

Set up Kong Gateway 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 Kong Gateway tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Kong Gateway 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="Kong Gateway Analyst",
        goal="Access and analyze Kong Gateway data via MCP.",
        backstory="Expert analyst with direct Kong Gateway access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kong Gateway 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 Kong Gateway. 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 Kong Gateway 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 Kong Gateway MCP in CrewAI

You can pass the Vinkius MCP Server URL directly into the agent's `mcps` array during initialization. This grants that specific agent access to tools like `get_service` and `update_route`. Other agents in the crew remain sandboxed without access to your gateway tools.

Yes, CrewAI supports hierarchical execution where a manager agent delegates tasks to specialized sub-agents. For example, one agent can run `get_service` to inspect the configuration, while a separate agent executes `update_service` to apply changes based on that inspection.

If a tool call like `create_plugin` fails due to a schema error or duplicate entry, the agent receives the error details. The agent then analyzes the issue, modifies its input parameters, and retries the operation automatically.

The integration supports stdio, SSE, and Streamable HTTP transports. For most multi-agent deployments, passing the Vinkius HTTP endpoint directly into the agent's setup is the simplest way to establish a secure connection.

All communications between CrewAI and the MCP server are encrypted in transit. The server only interacts with your Kong Gateway admin API to execute requested operations like listing consumers or updating routes. Your infrastructure configurations and credentials remain isolated inside Vinkius.

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