PluginBench
MCP Server
Active

io.github.kubeshop/testkube-mcp MCP Server

io.github.kubeshop/testkube-mcp

AI-driven test orchestration platform for Kubernetes—manage workflows, executions, and artifacts via MCP.

RepositoryRegistry

What is the io.github.kubeshop/testkube-mcp MCP server?

The Testkube MCP server enables AI assistants to manage test workflows, executions, and artifacts within Testkube, an open testing platform for Kubernetes. It provides programmatic access to trigger tests, view results, and analyze test data through the Model Context Protocol.

Testkube is a unified testing platform that runs any tests (API, E2E, performance, security, infrastructure) at scale in Kubernetes. The MCP server integration allows AI agents like Claude to interact with Testkube—triggering tests, retrieving results, and troubleshooting failures—making test management and analysis conversational and automated.

How to install io.github.kubeshop/testkube-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • TK_ACCESS_TOKEN
    required
    secret

    Testkube access token for authentication

  • TK_ORG_ID
    required

    Testkube organization ID

  • TK_ENV_ID
    required

    Testkube environment ID

  • TK_CONTROL_PLANE_URL

    Testkube Control Plane URL (default: https://api.testkube.io)

  • TK_DASHBOARD_URL

    Testkube Dashboard URL

  • TK_DEBUG

    Enable debug mode (default: false)

  • TK_MCP_TRANSPORT

    MCP transport type: stdio or shttp (default: stdio)

  • TK_MCP_SHTTP_HOST

    SHTTP host when using shttp transport

  • TK_MCP_SHTTP_PORT

    SHTTP port when using shttp transport

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "testkube-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/kubeshop/mcp-server:2.9.1"
      ],
      "env": {
        "TK_ACCESS_TOKEN": "<YOUR_TK_ACCESS_TOKEN>",
        "TK_ORG_ID": "<YOUR_TK_ORG_ID>",
        "TK_ENV_ID": "<YOUR_TK_ENV_ID>",
        "TK_CONTROL_PLANE_URL": "<YOUR_TK_CONTROL_PLANE_URL>",
        "TK_DASHBOARD_URL": "<YOUR_TK_DASHBOARD_URL>",
        "TK_DEBUG": "<YOUR_TK_DEBUG>",
        "TK_MCP_TRANSPORT": "<YOUR_TK_MCP_TRANSPORT>",
        "TK_MCP_SHTTP_HOST": "<YOUR_TK_MCP_SHTTP_HOST>",
        "TK_MCP_SHTTP_PORT": "<YOUR_TK_MCP_SHTTP_PORT>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • Test Workflow Management — Create, configure, and manage test workflows in Testkube
  • Test Execution — Trigger and execute tests manually, on schedules, or via API
  • Results & Artifacts — Access test results, logs, artifacts, and resource metrics
  • Test Analysis — Analyze test failures and retrieve detailed execution data

Use cases

  • Trigger test suites and monitor execution status through conversational AI prompts
  • Retrieve and analyze test results, logs, and artifacts for troubleshooting
  • Generate test workflows and remediation strategies using AI-driven insights
  • Integrate test automation into CI/CD pipelines via MCP protocol
  • Investigate test failures and get AI-powered recommendations for fixes

io.github.kubeshop/testkube-mcp MCP server FAQ

What is the Testkube MCP server?

It's an MCP integration that connects AI assistants (Claude, Cursor) to Testkube, allowing you to manage test workflows, trigger executions, and analyze results conversationally.

Is Testkube free?

Yes, Testkube has an MIT-licensed open-source agent that runs standalone in your Kubernetes cluster. A commercial control plane with advanced features (multi-cluster orchestration, Testkube AI, enterprise SSO) is also available.

How do I install the Testkube MCP server?

The server is available as a Docker image (docker.io/kubeshop/mcp-server:2.9.1). Configure it in your MCP client (Cursor, Claude) following the MCP server setup documentation.

What authentication is required?

You need access to a running Testkube instance (open-source agent or commercial control plane) with appropriate API credentials to connect the MCP server.

Can I use it with existing test tools?

Yes, Testkube supports any tests/tools/scripts (API, E2E, performance, security, infrastructure tests) and the MCP server provides AI access to manage them.

What can I do with the MCP server?

Trigger tests, retrieve execution results and logs, analyze failures, manage test workflows, and integrate testing into AI-driven automation and troubleshooting workflows.

README (reference)

Source of truth, from the repository.

MCP Toplist

<picture> <source media="(prefers-color-scheme: dark)" srcset="./assets/testkube_logo-light.png"> <source media="(prefers-color-scheme: light)" srcset="./assets/testkube_logo-dark.png"> <img alt="Testkube" src="./assets/testkube_logo-light.png"> </picture>

The Open Testing Platform for AI-driven Engineering Teams

Testkube provides a single platform for defining, running and analyzing automated tests, using your existing testing tools/scripts, running in your Kubernetes infrastructure.

<a href="#open-source-agent---this-repo"> <img src="https://img.shields.io/badge/Testkube%20OSS%20Agent-Get%20Started-lightgrey?style=for-the-badge" alt="Testkube Open Source - Get Started" /></a> <a href="https://testkube.io/get-started?utm_campaign=40056390-2026%20-%20Thematic%20-%20Open%20Source&utm_source=Github&utm_medium=readme&utm_content=trynow-link"> <img src="https://img.shields.io/badge/Testkube%20Enterprise-Try%20Now-brightgreen?style=for-the-badge&logo=data:image/svg%2bxml;base64,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" /></a>

Trusted by Engineering Teams at CoreWeave, NVidia, Siemens, T-Mobile, Harvard, SwissCom, and many more..

Website |  Docs |  Changelog |  Blog |  Slack  |  LinkedIn  |  X

Why Testkube?

  • Run any Tests : Execute any tests/tools/scripts at scale; API, E2E, Performance, Security, Infrastructure, etc. - Examples & Guides.
  • Trigger Tests whenever needed: Trigger tests manually, on schedules, from CI/CD/GitOps pipelines, on Kubernetes Events, via the REST API, through MCP, etc. - Read More.
  • See Everything: All test results, artifacts, logs and resource-metrics are aggregated for centralized troubleshooting and reporting - Read More.
  • Integrate Natively: Testkube integrates with existing tools and infrastructure using Webhooks, the Testkube REST API or the MCP Server - see Integration Examples.
  • Testkube AI: Use the Testkube MCP Server or native AI Agents for troubleshooting, analysis, remediation, etc - Read More
  • Enterprise Ready: SSO/SCIM, RBAC, Teams, Resource-Groups, Audit-logs, etc. - Read More.

Testkube Dashboard

See it in action: Open the interactive TestWorkflows showcase to see how a workflow builds up from a single test to a fully orchestrated pipeline.

Two ways to run Testkube

Open Source Agent - this repo.

MIT-licensed, runs standalone in your Kubernetes cluster, no control plane required. Great for single-cluster setups, self-managed environments, and evaluating Testkube.

  • The Helm or CLI Installation will make it easy to deploy the agent into your target cluster.
  • The Quickstart is the easiest way to set up Testkube and run your first tests.

Check out the Testkube Open Source Overview to learn more about the open source deployment architecture.

Commercial Control Plane

The control plane connects every Testkube agent across clusters, teams, and environments into a single dashboard:

  • One control plane, unlimited clusters - orchestrate and analyze tests across clusters and regions
  • Testkube AI - workflow generation, failure investigation, remediation PRs
  • Enterprise-grade - SSO/SCIM, RBAC, audit logs, SLA-backed support

Check out the Installation Overview to learn more about different ways to deploy and run the Testkube Control Plane.

The online Trial is the easiest way to try the commercial Testkube offering - Get Started

Marketplace

The Testkube Marketplace provides an open and ready-to-use catalog of Testkube Workflows for Infrastructure Testing - Read More.

Documentation

Extensive documentation is available at docs.testkube.io.

Contributing

Check out our Contributors Guide and the Agent Architecture to find your way around our codebase and process.

If you want to contribute code, this reading order works well:

  1. CONTRIBUTING.md - contribution workflow, coding standards, and PR process
  2. DEVELOPMENT.md - local setup with Tilt and day-to-day development loop
  3. ARCHITECTURE.md - high-level system design and key code paths

Shout-out to our contributors 🎉 - you're great!

Go to contribution document to read more how can you help us 🔥

Feedback

Whether Testkube helps you or not, we would love to help and hear from you. Please join us on Slack to ask questions and let us know how we can make Testkube even better!

Related MCP servers

KUKubeStellar MCP logo

KubeStellar MCP

Active

AI-powered Kubernetes diagnostics, RBAC analysis, security checks, and app deployment via MCP

2
Go
Apache-2.0
View repository →
IOio.github.kuhumcst/dannet logo

io.github.kuhumcst/dannet

Active

Danish WordNet with rich lexical relationships and SPARQL access via MCP.

29
Clojure
MIT
View repository →
ZOZotero MCP logo

Zotero MCP

Active

Search your Zotero library and retrieve item metadata and full text within AI assistants.

161
Python
MIT
View repository →
KUKujolang.ai MCP logo

Kujolang.ai MCP

Active

Discover Kujo projects, tools, skills, workflows, and installation guidance with read-only tools.

0
JavaScript
MIT
View repository →
KUKultur.dev logo

Kultur.dev

Maintained

Cultural Intelligence Infrastructure for AI Agents — 200+ markets, 15 tones, 8 tools

0
MIT
View repository →
WEWeather MCP logo

Weather MCP

Maintained

An MCP server for weather information by @kulybaba

0
TypeScript
View repository →