How do I connect my self-hosted TestLink to an AI client?

You subscribe to the MCP on Vinkius and enter your instance Base URL and Developer API Key. Once connected, your AI client can immediately start querying your data.

Which AI clients can I use with this MCP?

This MCP works with any compatible client, including Claude, Cursor, and Windsurf.

Do I need to change anything in my TestLink setup?

You will need your TestLink Base URL and a valid Developer API Key to allow the MCP to communicate with your instance.

Can I see the actual test steps in my chat?

Yes, you can ask your agent to retrieve the details of a specific test case, and it will provide the manual steps and expected results.

Is my data hosted by Vinkius?

Vinkius hosts and manages the MCP, handling the connection and credentials so it is ready to use immediately.

Why should I plug an AI agent into an older legacy application like TestLink?

Because retrieving test assets from older GUIs can be painfully slow for developers. By mapping the database to an AI agent, your devs can just chat: 'What are the steps to reproduce Test Case 4022?' The agent calls the XML-RPC backend and instantly formats the manual steps logically in the chat space.

Can it read all my hierarchical QA Suites and specific cases?

Yes! The testlink agent is configured to retrieve Suites. You just list a Project ID, traverse downwards into Test Suites, and then request Test Cases by the retrieved Suite ID. It allows full architectural transparency over chat.

Does my TestLink server need to be accessible to the internet?

No. Because MCP servers process logic strictly locally through a sidecar setup, the interaction happens right on your machine/endpoint. As long as the machine running the AI client (e.g. Cursor, Claude Desktop) can resolve the Internal Network URL, the connection is solid.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect TestLink to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pull test cases and build data directly into your AI chat.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through TestLink.

01
Get test case details
This capability pulls the full technical details for a specific test case, including steps and expected results.
02
Get test plan details
Use this to retrieve specific information regarding a single test plan.
03
Get test project details
This capability fetches the configuration and details for a specific TestLink project.
04
Get user info
This capability checks the identity and permissions of the authenticated user currently connected to TestLink.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through TestLink.

05
List test builds
This capability returns a list of all software builds associated with a given test plan.
06
List test cases
Use this to get a list of all test cases contained within a specific test suite.
07
List test plans
This capability lists every test plan tied to a specific project ID.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through TestLink.

08
List test projects
This capability provides a list of all available test projects on your TestLink instance.
09
List test suites
Use this to browse the folder hierarchy of test suites within a project.
10
Get test suite details
This capability retrieves the specific details and metadata for a single test suite.

Real work

What teams actually run

Regression Planning

QA Leads can quickly list all test plans for a project to prepare for a new release.

Bug Investigation

Developers can check the exact preconditions of a failing test case to reproduce bugs.

Test Documentation

Engineers can pull manual test steps into their documentation capabilities using natural language.

Build Verification

Teams can confirm which software builds are currently targeted in a specific test plan.

Automate a task

Put TestLink to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

TestLink works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put TestLink to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

903ms average. Fast in production.

TestLink is checked daily against the live service.

Daily averagePeak 1063ms

Oct 3Today

Fastest day: 773ms
Slowest day: 1063ms
14-day trend: Slowing+21%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of TestLink, so you can see the experience inside your AI.

It does not authenticate your account with TestLink. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

TestLink Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_Txd0bdinEzyETBUMcUstyIr6u481CAjFsmC77a1k/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — TestLink capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "testlink-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Txd0bdinEzyETBUMcUstyIr6u481CAjFsmC77a1k/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up TestLink in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work TestLink owners hand off.

This MCP is built for technical teams who manage testing through TestLink and want to move faster.

01
QA Leads
They pull test plans and historical cases into chat to define regression cycles.
02
Test Engineers
They recall step-by-step instructions from legacy cases directly into markdown editors.
03
Developers
They verify preconditions and expected results for bugs without needing UI access.

FAQ

Questions TestLink owners ask.

01
How do I connect my self-hosted TestLink to an AI client?
You subscribe to the MCP on Vinkius and enter your instance Base URL and Developer API Key. Once connected, your AI client can immediately start querying your data.
02
Which AI clients can I use with this MCP?
This MCP works with any compatible client, including Claude, Cursor, and Windsurf.
03
Do I need to change anything in my TestLink setup?
You will need your TestLink Base URL and a valid Developer API Key to allow the MCP to communicate with your instance.
04
Can I see the actual test steps in my chat?
Yes, you can ask your agent to retrieve the details of a specific test case, and it will provide the manual steps and expected results.
05
Is my data hosted by Vinkius?
Vinkius hosts and manages the MCP, handling the connection and credentials so it is ready to use immediately.
06
Why should I plug an AI agent into an older legacy application like TestLink?
Because retrieving test assets from older GUIs can be painfully slow for developers. By mapping the database to an AI agent, your devs can just chat: 'What are the steps to reproduce Test Case 4022?' The agent calls the XML-RPC backend and instantly formats the manual steps logically in the chat space.
07
Can it read all my hierarchical QA Suites and specific cases?
Yes! The testlink agent is configured to retrieve Suites. You just list a Project ID, traverse downwards into Test Suites, and then request Test Cases by the retrieved Suite ID. It allows full architectural transparency over chat.
08
Does my TestLink server need to be accessible to the internet?
No. Because MCP servers process logic strictly locally through a sidecar setup, the interaction happens right on your machine/endpoint. As long as the machine running the AI client (e.g. Cursor, Claude Desktop) can resolve the Internal Network URL, the connection is solid.

Explore

More in Developer Tools

Connect TestLink to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Get test case details

Get test plan details

Get test project details

Get user info

05-07

List test builds

List test cases

List test plans

08-10

List test projects

List test suites

Get test suite details

What teams actually run

Regression Planning

Bug Investigation

Test Documentation

Build Verification

Building your own app? The connector is yours to use.

TestLink Connector

Claude Desktop

QA Leads

Test Engineers

Developers

How do I connect my self-hosted TestLink to an AI client?

Which AI clients can I use with this MCP?

Do I need to change anything in my TestLink setup?

Can I see the actual test steps in my chat?

Is my data hosted by Vinkius?

Why should I plug an AI agent into an older legacy application like TestLink?

Can it read all my hierarchical QA Suites and specific cases?

Does my TestLink server need to be accessible to the internet?

Katalon TestOps (AI Test Management) AI Connector

Xray (Test Management) AI Connector

Zephyr Scale (SmartBear) AI Connector

TestRail AI Connector

Suggestions

Testim AI Connector

TestMonitor AI Connector

Mosaic (Resource Planning & Workforce Management) AI Connector

PractiTest AI Connector