Kong Konnect

by kong

22 stars
416 downloads
Not rated
GitHub Website

About

Integrates with Kong API Gateway to enable management and analysis of API configurations, traffic patterns, and control plane settings through Kong's cloud APIs for DevOps teams maintaining API infrastructure.

Details

Author
kong
Repository
Kong/mcp-konnect
GitHub stars
22
Downloads
416
License
Apache License 2.0
Categories
Cloud Service, API, Infrastructure, Other, AI, Workplace, Developer Tools, Search, Security, Communication

Jump to

- Query API request analytics with customizable filters
- List and inspect gateway services, routes, consumers, and plugins
- Manage control planes and control plane groups
- Integration with Claude and other MCP‑compatible AI assistants

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Kong Konnect
    Command (node, npx, python, etc.) node
    Arguments
    • Argument 1 /absolute/path/to/mcp-konnect/build/index.js
    Environment
    • KONNECT_REGION us
    • KONNECT_ACCESS_TOKEN kpat_api_key_here

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Set the following environment variables to configure the MCP server:

```bash

npm install

Query API Requests

Query and analyze Kong API Gateway requests with customizable filters. Inputs: timeRange (string), statusCodes (optional string), excludeStatusCodes (optional string), httpMethods (optional string), consumerIds (optional string), serviceIds (optional string), routeIds (optional string), maxResults (number)

Get Consumer Requests

Analyze API requests made by a specific consumer. Inputs: consumerId (string), timeRange (string), successOnly (boolean), failureOnly (boolean), maxResults (number)

List Services

List all services associated with a control plane. Inputs: controlPlaneId (string), size (number), offset (string)

List Routes

List all routes associated with a control plane. Inputs: controlPlaneId (string), size (number), offset (string)

List Consumers

List all consumers associated with a control plane. Inputs: controlPlaneId (string), size (number), offset (string)

List Plugins

List all plugins associated with a control plane. Inputs: controlPlaneId (string), size (number), offset (string), includeRawConfig (boolean)

List Control Planes

List all control planes in your organization. Inputs: pageSize (number), pageNumber (number), filterName (string), filterClusterType (string), filterCloudGateway (string), labels (string), sort (string)

Get Control Plane

Get detailed information about a specific control plane. Inputs: controlPlaneId (string)

List Control Plane Group Memberships

List all control planes that are members of a specific group. Inputs: groupId (string), pageSize (number), pageAfter (string)

Check Control Plane Group Membership

Check if a control plane is a member of any group. Inputs: controlPlaneId (string)

The server provides tools organized in three categories:

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "kong konnect": {
            "env": {
                "KONNECT_REGION": "us",
                "KONNECT_ACCESS_TOKEN": "kpat_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-konnect/build/index.js"
            ],
            "command": "node"
        }
    }
}

Linux

{
    "env": {
        "KONNECT_REGION": "us",
        "KONNECT_ACCESS_TOKEN": "kpat_api_key_here"
    },
    "args": [
        "/absolute/path/to/mcp-konnect/build/index.js"
    ],
    "command": "node"
}

Macos

{
    "env": {
        "KONNECT_REGION": "us",
        "KONNECT_ACCESS_TOKEN": "kpat_api_key_here"
    },
    "args": [
        "/absolute/path/to/mcp-konnect/build/index.js"
    ],
    "command": "node"
}

Windows

{
    "env": {
        "KONNECT_REGION": "us",
        "KONNECT_ACCESS_TOKEN": "kpat_api_key_here"
    },
    "args": [
        "/absolute/path/to/mcp-konnect/build/index.js"
    ],
    "command": "node"
}

Interact with Kong Konnect APIs to query and analyze Kong Gateway configurations, traffic, and analytics.

This project is no longer actively maintained and will be archived as read-only.

No further updates, bug fixes, or new features will be made. Issues and pull requests are no longer monitored.

If you're looking for Kong Konnect MCP support, please check theKonnect remote MCP server.

Note:This repository is deprecated and will soon be archived as read-only. See the notice above for details.

A Model Context Protocol (MCP) server for interacting with Kong Konnect APIs, allowing AI assistants to query and analyze Kong Gateway configurations, traffic, and analytics.

- Overview
- Project Structure
- Installation
- Configuration
- Available Tools

- Analytics Tools
- Configuration Tools
- Control Planes Tools

⚠️ Deprecated:This project is no longer maintained. The information below is preserved for reference only.

This project provides a Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with Kong Konnect's API Gateway. It offers a set of tools to query analytics data, inspect configuration details, and manage control planes through natural language conversation.

- Query API request analytics with customizable filters
- List and inspect gateway services, routes, consumers, and plugins
- Manage control planes and control plane groups
- Integration with Claude and other MCP-compatible AI assistants

build/ # Committed compiled JavaScript output used by the release/distribution flow src/ ├── index.ts # Main entry point ├── api.ts # Kong API client ├── tools.ts # Tool definitions ├── parameters.ts # Zod schemas for tool parameters ├── prompts.ts # Detailed tool documentation ├── operations/ │ ├── analytics.ts # API request analytics operations │ ├── configuration.ts # Services, routes, consumers, plugins │ └── controlPlanes.ts # Control plane management └── types.ts # Common type definitions

Note:As this project is deprecated, no support is provided for installation issues.

- Node.js 20 or higher
- A Kong Konnect account with API access
- A client with MCP capabilities (e.g. Claude Desktop, Cursor, etc...)

# Clone the repository git clone https://github.com/Kong/mcp-konnect.git cd mcp-konnect # Install dependencies npm install # Run the test suite (also rebuilds compiled output) npm test # Rebuild the committed build artifacts after changing src/ npm run build

The repository includes committed files underbuild/as part of its distribution model. If you modify files insrc/, regeneratebuild/before committing or publishing changes.

Set the following environment variables to configure the MCP server:

# Required: Your Kong Konnect API key export KONNECT_ACCESS_TOKEN=kpat_api_key_here # Optional: The API region to use (defaults to US) # Possible values: US, EU, AU, ME, IN export KONNECT_REGION=us

The server provides tools organized in three categories:

Query and analyze Kong API Gateway requests with customizable filters.

Inputs: - timeRange: Time range for data retrieval (15M, 1H, 6H, 12H, 24H, 7D) - statusCodes: Filter by specific HTTP status codes - excludeStatusCodes: Exclude specific HTTP status codes - httpMethods: Filter by HTTP methods - consumerIds: Filter by consumer IDs - serviceIds: Filter by service IDs - routeIds: Filter by route IDs - maxResults: Maximum number of results to return

Analyze API requests made by a specific consumer.

Inputs: - consumerId: ID of the consumer to analyze - timeRange: Time range for data retrieval - successOnly: Show only successful (2xx) requests - failureOnly: Show only failed (non-2xx) requests - maxResults: Maximum number of results to return

List all services associated with a control plane.

Inputs: - controlPlaneId: Control plane ID - size: Number of services to return - offset: Pagination offset token

List all routes associated with a control plane.

Inputs: - controlPlaneId: Control plane ID - size: Number of routes to return - offset: Pagination offset token

List all consumers associated with a control plane.

Inputs: - controlPlaneId: Control plane ID - size: Number of consumers to return - offset: Pagination offset token

List all plugins associated with a control plane.

Inputs: - controlPlaneId: Control plane ID - size: Number of plugins to return - offset: Pagination offset token - includeRawConfig: Set to true to include raw plugin configuration values (defaults to false)

List all control planes in your organization.

Inputs: - pageSize: Number of control planes per page - pageNumber: Page number to retrieve - filterName: Filter control planes by name - filterClusterType: Filter by cluster type - filterCloudGateway: Filter by cloud gateway capability - labels: Filter by labels - sort: Sort field and direction

Get detailed information about a specific control plane.

Inputs: - controlPlaneId: Control plane ID to retrieve

List all control planes that are members of a specific group.

Inputs: - groupId: Control plane group ID - pageSize: Number of members to return per page - pageAfter: Cursor for pagination

Check if a control plane is a member of any group.

Inputs: - controlPlaneId: Control plane ID to check

Note:This configuration is provided for historical reference. No support is available for setup issues.

To use this MCP server with Claude for Desktop:

Create or edit the Claude Desktop configuration file:

- MacOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "kong-konnect": { "command": "node", "args": [ "/absolute/path/to/mcp-konnect/build/index.js" ], "env": { "KONNECT_ACCESS_TOKEN": "kpat_api_key_here", "KONNECT_REGION": "us" } } } }

- Restart Claude for Desktop
- The Kong Konnect tools will now be available for Claude to use

Please list all control planes in my Kong Konnect organization.

Then, list services for a specific control plane:

List all services for control plane [CONTROL_PLANE_ID].

Query API requests for a specific service:

Show me all API requests for service [SERVICE_NAME/ID] in the last hour that had 5xx status codes.

List all consumers for control plane [CONTROL_PLANE_ID].

Analyze requests for a specific consumer:

Show me all requests made by consumer [CONSUMER_NAME/ID] in the last 24 hours.

What are the most common errors experienced by this consumer?

⚠️ This project is no longer accepting contributions.The repository will be archived as read-only. Pull requests and issues will not be reviewed or merged.

- npm testruns the TypeScript build and the repository test suite.
- build/is a committed generated artifact in this repository and should be regenerated withnpm run buildafter changes tosrc/.

Note:No support is provided for this deprecated project. The information below is preserved for reference only.

- Verify your API key is valid and has the necessary permissions
- Check that the API region is correctly specified
- Ensure your network can connect to the Kong Konnect API

- Regenerate your API key in the Kong Konnect portal
- Check that environment variables are correctly set

- Verify the IDs used in requests are correct
- Check that the resources exist in the specified control plane
- Ensure time ranges are valid for analytics queries

Built by Kong. Originally inspired by Stripe'sAgent Toolkit.

Monitor sites, APIs, servers & SSL certs with UptimeRobot: manage monitors, incidents & stats.

ClawManager Fleet Control is a paid hosted remote MCP for ClawManager. It exposes Streamable HTTP tool calls, bearer-token access, public server-card metadata, usage logs, and receipt-orient

Manage and interact with Microsoft Azure services.

The IBM Instana MCP server enables seamless interaction with the IBM Instana observability platform, allowing you to access real-time observability data directly within your development workflow.

Query and interact with kubernetes environments monitored by Metoro

Automate Akamai resource actions using a conversational AI client. Requires Akamai API credentials.

Integrates with Alibaba Cloud APIs to manage resources like ECS, Cloud Monitor, and OOS.

Provides a unified interface to AWS services for security investigations and incident response.

Interact with your AWS environment using natural language to query and manage resources. Requires local AWS credentials.

Interact with your AWS environment using natural language. Requires local AWS credentials.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Install

Add to Claude Desktop or Cursor

{
    "mcpServers": {
        "kong konnect": {
            "env": {
                "KONNECT_REGION": "us",
                "KONNECT_ACCESS_TOKEN": "kpat_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-konnect/build/index.js"
            ],
            "command": "node"
        }
    }
}

More like this

Similar MCP servers you might find useful

Browse category

AWS MCP Servers

This AWS Labs Model Context Protocol (MCP) server for CloudTrail enables your AI agents to query AWS account activity for security investigations, compliance…

9.4k
Cloud Service

Browser Tools

Enables web browsing capabilities through tools for content extraction, link following, and browser automation with customizable parameters for scraping, data…

5.0 6.7k
Developer Tools

Git (GitHub to MCP)

GitMCP is a free, open-source, remote Model Context Protocol (MCP) server that transforms any GitHub project (repositories or GitHub pages) into a…

6.5k
Developer Tools