MCP Server for Test Management | Connect AI Assistants to TestCollab

Why use MCP

Test management meets AI-assisted development

Create tests while you code

Implementing a new feature? Ask your AI assistant to create test cases as you build. No context switching, no copy-paste - tests are created directly in TestCollab.

Keep tests in sync with code

Refactored a function? Changed an API response? Your AI assistant can find and update affected test cases automatically, keeping documentation current.

Query coverage before changes

Before touching authentication code, ask what tests exist. Filter by priority, status, or keywords. Make informed decisions about test impact.

Open protocol, open source

Built on Anthropic's Model Context Protocol standard. Works with Claude, Cursor, Windsurf, Codex, and any MCP-compatible client. MIT licensed.

Understanding MCP

What is an MCP Server?

The Model Context Protocol (MCP) is an open standard created by Anthropic that lets AI assistants connect to external tools and data sources. An MCP server exposes capabilities that AI assistants can discover and use.

A bridge between AI and your tools

MCP servers expose tools, resources, and prompts that AI assistants can use. Think of it as giving your AI assistant hands to interact with external systems - databases, APIs, file systems, or in this case, test management.

The TestCollab MCP server exposes 17 tools for test cases, suites, and test plans. Your AI assistant discovers these capabilities and uses them when relevant to your conversation.

Secure by design

MCP uses per-session authentication. Your API token is passed via environment variables - the server never stores credentials. Each session is isolated, and the AI assistant only accesses projects you authorize.

The protocol runs locally via stdio transport, keeping credentials on your machine.

Compatible AI IDEs

Works with your favorite AI tools

Any MCP-compatible client can connect to the TestCollab MCP server. Here are the most popular ones.

Claude Code

Anthropic's AI coding assistant with native MCP support. Configure via claude_desktop_config.json and start managing tests from your terminal or desktop app.

Cursor

The AI-first code editor built on VS Code. Add TestCollab to your MCP servers and create tests while you write code - all in the same window.

Codex CLI

OpenAI's command-line coding agent with MCP support. Add TestCollab to your config.toml and manage tests directly from your terminal.

What you can do

MCP Server Capabilities

17 tools for test cases, suites, and test plans — manage your entire test lifecycle from your AI assistant.

Manage test cases

Full test case lifecycle management:

- Create test cases with steps, tags, and custom fields
- Query with filters by priority, status, suite, or keyword
- Fetch full details including reusable steps
- Update any field — title, steps, expected results, tags

Organize test suites

Build and manage your suite hierarchy:

- Create suites with parent-child nesting
- List the full suite tree with filtering
- Move suites between parents or to root
- Reorder siblings to control sort order

Plan test execution

Create and manage test execution plans:

- Create plans with test cases and configurations
- Assign testers to specific configurations
- Filter by status, priority, date range, or folder
- Track progress with run summaries

Setup guide

Getting Started

Connect in under 5 minutes. Install via npx or run from source.

Option 1: Install via npx (recommended)

Add TestCollab to your MCP client config:

{
  "mcpServers": {
    "testcollab": {
      "command": "npx",
      "args": ["-y", "@testcollab/mcp-server"],
      "env": {
        "TC_API_TOKEN": "your-api-token",
        "TC_API_URL": "https://api.testcollab.io",
        "TC_DEFAULT_PROJECT": "your-project-id"
      }
    }
  }
}

Get your API token from TestCollab → Profile → API Token. See the setup guide for full config examples.

Option 2: Run from source

Clone and run the server locally for full control:

1. Clone the repo from GitHub
2. Run npm install and npm run build
3. Point your MCP client to node dist/index.js

See the README for environment configuration options.

FAQ

Answers teams look for

What is an MCP server?

An MCP (Model Context Protocol) server is a service that exposes tools, resources, and prompts to AI assistants. It's an open standard created by Anthropic that lets AI tools interact with external systems securely. The TestCollab MCP server lets AI assistants manage test cases, suites, and test plans.

Which AI assistants are supported?

Any MCP-compatible client works: Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI, and others. The protocol is open, so new clients are added regularly.

Is the MCP server open source?

Yes. The TestCollab MCP server is MIT licensed and available on GitHub at github.com/TCSoftInc/testcollab-mcp-server. Install via npx or clone and run from source.

How does authentication work?

The MCP server uses environment variable authentication. Pass your TestCollab API token via the TC_API_TOKEN environment variable in your MCP client config. Tokens are scoped to your user permissions - the AI assistant can only access projects you have access to.

Can I use this with self-hosted TestCollab?

Yes. Set the TC_API_URL environment variable to point to your self-hosted TestCollab instance. The MCP server sends all requests to whatever API URL you configure.

What operations are supported?

Test cases (list, get, create, update), test suites (list, get, create, update, delete, move, reorder), test plans (list, get, create, update, delete), plus a project context tool that loads your suite tree, tags, users, and custom fields so you can reference everything by name.

Is there rate limiting?

The MCP server respects TestCollab API rate limits. For most use cases with AI assistants, you won't hit limits. Enterprise plans have higher quotas.

MCP Server for AI-Powered Test Management