Vinkius
TestLink

TestLink MCP for AI. Query the entire test management structure via chat.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

TestLink MCP on Cursor AI Code EditorTestLink MCP on Claude Desktop AppTestLink MCP on OpenAI Agents SDKTestLink MCP on Visual Studio CodeTestLink MCP on GitHub Copilot AI AgentTestLink MCP on Google Gemini AITestLink MCP on Lovable AI DevelopmentTestLink MCP on Mistral AI AgentsTestLink MCP on Amazon AWS Bedrock

Connect to your AI in seconds.

TestLink MCP Server lets your AI agent access and navigate a self-hosted TestLink environment. It maps complex test data—from projects to individual cases—into natural conversation, letting you pull specific steps, check preconditions, or list active builds without touching the legacy UI.

What your AI can do

Get test case details

Retrieves the full manual steps, expected results, and metadata for one specific test case ID.

Get test plan details

Gets all details associated with a particular test plan instance.

Get test project details

Retrieves general information for a specific TestLink project ID.

+ 7 more capabilities included
List all available projects

Runs list_test_projects to retrieve a list of every test project on the server.

Get detailed information for a specific test plan

Uses get_test_plan_details to pull all metadata associated with a chosen test plan.

Walk through the suite structure

Runs list_test_suites or list_test_cases to map out the full folder and category tree of your tests.

Retrieve specific test case instructions

Calls get_test_case_details to output manual steps, expected results, and preconditions for a single ID.

Track software builds against plans

Executes list_test_builds to confirm which versions of the application are tied to a specific test plan.

Verify user context

Runs get_user_info to check the API token's authenticated status and permissions within TestLink.

Included with Plan

Waiting for input…

AI Agent

TestLink MCP Server: 10 Tools for QA Management

Use these tools to navigate TestLink's entire data model. Access project directories, plan details, test case instructions, and build histories using natural language queries.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using TestLink on Vinkius

Get Test Case Details

Retrieves the full manual steps, expected results, and metadata for one specific test case ID.

Get Test Plan Details

Gets all details associated with a particular test plan instance.

Get Test Project Details

Retrieves general information for a specific TestLink project ID.

Get Test Suite Details

Gets details about a defined test suite, including its parent and scope.

List Test Builds

Lists all available software builds that are linked to a specific test plan ID.

List Test Cases

Outputs a list of every individual test case found within a designated test suite.

List Test Plans

Lists all defined test plans that belong to a specific project ID.

List Test Projects

Retrieves a directory listing of every major test project on the server.

List Test Suites

Lists all defined test suites that are contained within a specific test project ID.

Get User Info

Checks the API token's current user identity and authentication status within...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Claude AI

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

3

Start a conversation

Open a new chat. The TestLink integration is available immediately — no restart needed.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

  • Import from OpenAPI, Swagger, or YAML specs
  • Create Agent Skills with progressive disclosure
  • Deploy to edge with MCPFusion framework
  • Built in DLP, auth, and compliance on every call
  • Real time usage dashboard and cost metering
  • Publish to catalog or keep private
Start building

Make Your AI Do More

Start with TestLink, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

  • Use this MCP plus 5,000+ others, all in one place
  • Add new capabilities to your AI anytime you want
  • Every connection is secured and compliant automatically
  • Track usage and costs across all your servers
  • Works with Claude, ChatGPT, Cursor, and more
  • New servers added to the catalog every week
TestLink MCP server cover

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by TestLink. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Navigating test environments used to feel like clicking through ten different tabs in a browser.

Today, finding specific test data is a pain. You start on the Project dashboard, then click into Plan X. Once there, you have to drill down to the Suite folder, and finally find the Test Case ID under that structure. If you need three different pieces of info—say, preconditions, builds, and plan details—you copy-paste between four different pages just to compile a single report.

With this MCP server, it’s direct. You tell your agent: 'Give me the preconditions for Test Case ID 5440 and list all associated test builds.' The toolset runs `get_test_case_details` and `list_test_builds` simultaneously and sends you a single, clean output block. No clicks required.

TestLink MCP Server: Get the full context of any Test Case.

Before this toolset, getting full context meant checking multiple views—the main case view for steps, a separate tab for preconditions, and another screen to check related builds. It was tedious copy-pasting just to confirm the status quo.

Now, you use `get_test_case_details`. You get all that data in one go: the manual steps, the expected result, the priority, and the necessary prerequisites—all pulled into your chat window instantly.

What your AI can actually do with this

Listen up, pal. You gotta connect your self-hosted TestLink setup to any AI agent and ditch that clunky old UI. This server exposes every core function of TestLink as actionable tools for your agent. It maps all that complex test data—from the biggest projects down to tiny individual steps—right into natural chat conversation.

Your AI client handles all the heavy lifting, letting you pull specific steps, check preconditions, or list active builds without ever touching a legacy dashboard.

Project Discovery and Scope Management
You'll start by seeing what big picture stuff is going on. You can run list_test_projects to get a directory listing of every major test project sitting on the server. When you know which project you wanna dig into, use get_test_project_details to grab all the general info for that specific TestLink project ID.

Navigating the Hierarchy
To walk through your entire suite structure, first check out the projects with list_test_projects, then jump in and run list_test_suites to get a list of every defined test suite tied to a project. If you need more depth on those suites, call get_test_suite_details for details about a specific suite, including its parent scope.

From there, you can map out the whole folder and category tree by calling list_test_cases, which outputs every individual test case found within that designated test suite. For the nitty-gritty on any single item, you'll use get_test_case_details to pull all manual steps, expected results, metadata, and preconditions for a specific test case ID.

Testing Plans and Builds
If your goal is tracking what needs testing, start by listing the plans themselves. Run list_test_plans to get every defined test plan belonging to a project. Grab all the associated data using get_test_plan_details for a chosen instance. When you need to know which versions of the app are tied to that plan, execute list_test_builds.

This function confirms exactly which software builds are linked to a specific test plan ID.

Checking Context and Permissions
Before you start pulling data, you gotta make sure your agent has clearance. Use get_user_info to check the API token's authenticated status and see what user identity it’s running under within TestLink.

This toolset lets you query the full lifecycle of a software test, allowing your agent to verify your authentication context via get_user_info, retrieve general project info using get_test_project_details, list all available projects with list_test_projects, and drill down through the structure. You can then use list_test_suites or get_test_suite_details to map out the full category tree, listing every case via list_test_cases.

To get the deep details on a plan, run list_test_plans followed by get_test_plan_details, and confirm linked software versions with list_test_builds. Finally, when you're down to the actual procedure, call get_test_case_details for all the steps, expected results, and metadata on that single test case. You'll get every piece of data without having to look at a messy web interface.

Built · Hosted · Managed by Vinkius TestLink MCP Server - Manage QA Test Plans and Cases
Server ID 019d7611-e687-729c-9774-26ca30a31aeb
Vinkius Inspector
Compliance Grade A+
Score 100/100
Vinkius Inspector Badge — Score 100/100

Questions you might have

How do I list all projects using list_test_projects? +

Run list_test_projects with no arguments. It returns a list of every major project ID available on the server, which you can then use for subsequent queries.

What is the difference between list_test_plans and list_test_suites? +

list_test_projects gives you projects. You must first find a Project ID, and then you can run list_test_plans on that project to get plans; suites are nested deeper within the plan structure.

Can I check who my API token is? +

Yes, use get_user_info. This tool runs a check against the server and confirms your user identity and associated privileges for the current session.

Do I need to provide an ID every time I call get_test_case_details? +

Yes. get_test_case_details requires a specific Test Case ID as an argument. You can't query it without knowing the exact identifier.

How do I use list_test_builds to check which versions are available for a test plan? +

You must pass the specific Test Plan ID to list_test_builds. This returns all software builds linked to that plan's scope, letting you verify if your test steps align with the exact QA target version you need to validate against.

What happens if I use get_test_suite_details with an incorrect ID? +

The function immediately returns a specific error code stating that the requested resource was not found. This confirms either the Suite ID is wrong or it doesn't belong to the Project ID you provided, allowing you to fix your query scope fast.

Does get_test_case_details provide all necessary information in one call? +

Yes. It retrieves comprehensive details including preconditions, manual step sequences, expected results, and priority levels. You don't need to jump through the legacy UI just to compile a single report.

If I call list_test_cases many times in quick succession, are there usage limits? +

Vinkius manages standard rate limiting for this endpoint. Too many calls in a short time will result in an HTTP 429 error. Wait a minute or two and try again to avoid service disruption.

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.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for TestLink. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.