Configure AI Gateway passthrough for existing MCP Servers
Configure AI Gateway passthrough for existing MCP Servers to enable proxying and observability.
For this configuration to work properly, you need a Service and a Route with the following configuration:
services: - name: mcp-service url: http://host.docker.internal:3000 routes: - name: mcp-route paths: - /marketplaceCopied!
Before using the AI MCP Proxy plugin, you’ll need an upstream HTTP API to expose.
Use this mock API to test the plugin without relying on an external service; it simulates a small marketplace with sample users and orders exposed through /marketplace/users and /marketplace/{userId}/orders endpoints:
curl -s -o api.js "https://gist.githubusercontent.com/subnetmarco/5ddb23876f9ce7165df17f9216f75cce/raw/a44a947d69e6f597465050cc595b6abf4db2fbea/api.js"
npm install express
node api.js
Prerequisites
- A running and exposed API
Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: ai-mcp-proxy
config:
mode: passthrough-listener
max_request_body_size: 1048576
Make the following request:
curl -i -X POST http://localhost:8001/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-mcp-proxy",
"config": {
"mode": "passthrough-listener",
"max_request_body_size": 1048576
},
"tags": []
}
'
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-mcp-proxy",
"config": {
"mode": "passthrough-listener",
"max_request_body_size": 1048576
},
"tags": []
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongClusterPlugin
metadata:
name: ai-mcp-proxy
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
konghq.com/tags: ''
labels:
global: 'true'
config:
mode: passthrough-listener
max_request_body_size: 1048576
plugin: ai-mcp-proxy
" | kubectl apply -f -
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_mcp_proxy" "my_ai_mcp_proxy" {
enabled = true
config = {
mode = "passthrough-listener"
max_request_body_size = 1048576
}
tags = []
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}
Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: ai-mcp-proxy
service: serviceName|Id
config:
mode: passthrough-listener
max_request_body_size: 1048576
Make sure to replace the following placeholders with your own values:
-
serviceName|Id: Theidornameof the service the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/services/{serviceName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-mcp-proxy",
"config": {
"mode": "passthrough-listener",
"max_request_body_size": 1048576
},
"tags": []
}
'
Make sure to replace the following placeholders with your own values:
-
serviceName|Id: Theidornameof the service the plugin configuration will target.
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/services/{serviceId}/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-mcp-proxy",
"config": {
"mode": "passthrough-listener",
"max_request_body_size": 1048576
},
"tags": []
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane. -
serviceId: Theidof the service the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-mcp-proxy
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
konghq.com/tags: ''
config:
mode: passthrough-listener
max_request_body_size: 1048576
plugin: ai-mcp-proxy
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the service resource:
kubectl annotate -n kong service SERVICE_NAME konghq.com/plugins=ai-mcp-proxy
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_mcp_proxy" "my_ai_mcp_proxy" {
enabled = true
config = {
mode = "passthrough-listener"
max_request_body_size = 1048576
}
tags = []
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
service = {
id = konnect_gateway_service.my_service.id
}
}
Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: ai-mcp-proxy
route: routeName|Id
config:
mode: passthrough-listener
max_request_body_size: 1048576
Make sure to replace the following placeholders with your own values:
-
routeName|Id: Theidornameof the route the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/routes/{routeName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-mcp-proxy",
"config": {
"mode": "passthrough-listener",
"max_request_body_size": 1048576
},
"tags": []
}
'
Make sure to replace the following placeholders with your own values:
-
routeName|Id: Theidornameof the route the plugin configuration will target.
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/routes/{routeId}/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-mcp-proxy",
"config": {
"mode": "passthrough-listener",
"max_request_body_size": 1048576
},
"tags": []
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane. -
routeId: Theidof the route the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-mcp-proxy
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
konghq.com/tags: ''
config:
mode: passthrough-listener
max_request_body_size: 1048576
plugin: ai-mcp-proxy
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the httproute or ingress resource:
kubectl annotate -n kong httproute konghq.com/plugins=ai-mcp-proxy
kubectl annotate -n kong ingress konghq.com/plugins=ai-mcp-proxy
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_mcp_proxy" "my_ai_mcp_proxy" {
enabled = true
config = {
mode = "passthrough-listener"
max_request_body_size = 1048576
}
tags = []
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
route = {
id = konnect_gateway_route.my_route.id
}
}