What is kong-konnect?

A set of coding-agent instructions and remote connections for managing Kong Konnect, Kong’s cloud platform for running and publishing APIs.

Managing gateways, API catalogs, publishing, access scopes, authentication, observability, portals, Terraform configurations, and related Kong platform setup.

It gives an agent guidance for common Kong Konnect tasks instead of requiring every workflow to be described from scratch.

kong-konnect — Plugin for Claude Code by Kong/ai-marketplace

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Kong/ai-marketplace

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/kong/ai-marketplace/kong-konnect/github.svg)](https://agentmods.dev/plugins/kong/ai-marketplace/kong-konnect)

Your own site

<a href="https://agentmods.dev/plugins/kong/ai-marketplace/kong-konnect"><img src="https://agentmods.dev/badge/plugins/kong/ai-marketplace/kong-konnect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/kong/ai-marketplace/kong-konnect"><img src="https://agentmods.dev/badge/plugins/kong/ai-marketplace/kong-konnect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 22 skills, 1 MCP server cost 1,181 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

kong-konnect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/kong-konnect/.claude-plugin/plugin.json · 39 lines

What it actually says

{
  "name": "kong-konnect",
  "version": "1.0.0",
  "description": "Kong Konnect skills and the hosted Konnect MCP server for managing AI and API gateways from Claude Code.",
  "author": {
    "name": "Kong",
    "url": "https://konghq.com"
  },
  "skills": [
    "./skills/deck-gateway",
    "./skills/gateway-plugin-datakit",
    "./skills/kong-skill-authoring",
    "./skills/kongctl-declarative",
    "./skills/kongctl-query",
    "./skills/konnect-access-scope",
    "./skills/konnect-ai-gateway",
    "./skills/konnect-api-catalog",
    "./skills/konnect-api-publish",
    "./skills/konnect-app-auth",
    "./skills/konnect-control-plane-bootstrap",
    "./skills/konnect-event-gateway",
    "./skills/konnect-gateway-triage",
    "./skills/konnect-monetization",
    "./skills/konnect-observability-triage",
    "./skills/konnect-platform-router",
    "./skills/konnect-reference-platform",
    "./skills/portal-branding",
    "./skills/portal-page-design",
    "./skills/technical-writing",
    "./skills/terraform-kong-gateway",
    "./skills/terraform-konnect"
  ],
  "mcpServers": "./mcp.json",
  "privacyPolicyUrl": "https://konghq.com/legal/privacy-policy",
  "license": "MIT",
  "homepage": "https://developer.konghq.com/konnect-platform/konnect-mcp/",
  "repository": "https://github.com/Kong/ai-marketplace"
}

Contents

What it installs

The manifest is a name and a version. 22 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 1,181 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

28d ago Changed · +1 lines ae634d50ff28
1mo ago Changed · +5 lines 03a2ca835258
1mo ago Changed 2098cff5e029
2mo ago First seen · 33 lines scan A 20f210322e5f

Subscribe to this mod's changes

kong-konnect is a plugin published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs agent-skills agentic-workflows agents ai kong kong-gateway

kong-konnect next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kong-konnectKong/ai-marketplace	Plugin	6	10d ago	MIT	A	—	Claude Code
azure-sdk-dotnetmicrosoft/skills	Plugin	3.2k	yesterday	MIT	A	—	Claude Code
contentfulcontentful/skills	Plugin	40	yesterday	MIT	A	—	Claude Code
contentfulcontentful/skills	Plugin	40	yesterday	MIT	A	—	Claude Code
typefox-agent-skillsTypeFox/agent-skills	Plugin	5	15d ago	MIT	A	—	Claude Code
powabasepowabase-ai/agent-skills	Plugin	9	1mo ago	Apache-2.0	A	—	Gemini CLI
humanizerblader/humanizer	Plugin	65k	10d ago	MIT	A	—	Claude Code