How to Use the Kong (AI API Gateway) MCP in CrewAI

Q: How do I connect Kong (AI API Gateway) to my CrewAI setup?

Pass the Vinkius endpoint directly into your agent's mcps array. The framework automatically discovers the tools and makes them available to the assigned crew members.

Q: Can a CrewAI agent monitor Kong (AI API Gateway) routing rules?

Yes. You assign an MCP agent to run listroutes on a schedule. It pulls the current rules, compares them against your desired state, and alerts you if they drift.

Q: How do multiple agents share Kong (AI API Gateway) credentials?

The crew shares context memory. If one agent runs createconsumerkey, the resulting token is stored in the session memory for other agents to reference during their tasks.

Q: How do I restrict which tools an agent can use?

Import MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give your read-only agent access to listservices while restricting createroute to your admin agent.

Deploy a team of autonomous CrewAI agents to manage and monitor your Kong gateway.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kong (AI API Gateway) MCP to CrewAI

Create your Vinkius account to connect Kong (AI API 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 (AI API Gateway) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate gateway routing to CrewAI agents

The `create_service` tool maps upstream LLM provider endpoints into your gateway via this MCP server. You assign this to an infrastructure agent, which reads your architecture requirements and provisions the backend automatically. A secondary networking agent then takes over, executing `create_route` to expose that service. They share memory, so the networking agent knows exactly which service ID the infrastructure agent just created.

Manage AI proxy plugins autonomously

Your security agent uses `create_ai_plugin` to enforce LLM routing and key encapsulation. It evaluates the current threat model and applies the appropriate rate limiting and proxy rules without human intervention. If a monitor agent detects unusual traffic patterns, it commands the moderation agent to run `update_plugin`. The moderation agent adjusts the rate limits dynamically to protect the upstream providers.

Audit configurations with this MCP Server

An auditor agent relies on `list_plugins` and `list_services` to map the active gateway state. It continuously polls the gateway to ensure no unauthorized endpoints exist. When it finds a violation, it triggers an escalation path. Another agent executes `delete_plugin` to strip the unapproved configuration, while a reporting agent uses `list_consumers` to identify who created the vulnerability.

Setup guide

Set up Kong (AI API 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 (AI API Gateway) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the Vinkius endpoint directly into your agent's `mcps` array. The framework automatically discovers the tools and makes them available to the assigned crew members.

Yes. You assign an MCP agent to run `list_routes` on a schedule. It pulls the current rules, compares them against your desired state, and alerts you if they drift.

The crew shares context memory. If one agent runs `create_consumer_key`, the resulting token is stored in the session memory for other agents to reference during their tasks.

Import `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. You can give your read-only agent access to `list_services` while restricting `create_route` to your admin agent.

The server only handles control plane data like route paths, plugin settings, and service definitions. Because Vinkius uses ephemeral sandboxing, your architectural state is wiped from memory the moment your crew finishes its task.

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