Kong Konnect MCP Server
Kong Konnect MCP Server
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.
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.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| timeRange | Time range for data retrieval |
| 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 |
| consumerId | ID of the consumer to analyze |
| successOnly | Show only successful (2xx) requests |
| failureOnly | Show only failed (non-2xx) requests |
| controlPlaneId | Control plane ID to check |
| size | Number of plugins to return |
| offset | Pagination offset token |
| includeRawConfig | Set to true to include raw plugin configuration values (defaults to false) |
| pageSize | Number of members to return 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 |
| groupId | Control plane group ID |
| pageAfter | Cursor for pagination |
{
"mcpServers": {
"kong-konnect": {
"command": "node",
"args": [
"/absolute/path/to/mcp-konnect/build/index.js"
],
"env": {
"KONNECT_ACCESS_TOKEN": "YOUR_KONNECT_ACCESS_TOKEN",
"KONNECT_REGION": "us"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| KONNECT_ACCESS_TOKEN | Declared in the maintainer’s client configuration. | Check documentation |
| KONNECT_REGION | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Runs coding-agent workers on a codebase question; every claim in the answer carries evidence.
Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
Score prompt quality across 8 dimensions before they reach a model. Pre-flight, not post-hoc.
Python framework for creating AI agents that use MCP servers as tools. Compatible with any MCP server and model provider.