Testcollab Mcp Server

Name: Testcollab Mcp Server
Author: TCSoftInc

@TCSoftInc

关于 Testcollab Mcp Server

Manage test cases directly from Claude, Cursor, Windsurf, and other MCP-compatible AI coding assistants. TestCollab serves as a governance layer and truth engine for AI-generated code - your test cases define what "correct" means, so when AI writes or modifies code, it has a clea

#testing #test-management #ai #qa #test-cases #governance

基本信息

分类

开发工具

传输方式

stdio

发布者

TCSoftInc

提交者

Abhimanyu Grover

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "testcollab": {
      "url": "https://mcp.testcollab.io/mcp",
      "transport": "sse"
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Testcollab Mcp Server?

A Model Context Protocol server that exposes TestCollab test management functionality to AI assistants like Claude. It enables creating, reading, and updating test cases with steps, custom fields, and attachments.

How to use Testcollab Mcp Server?

Install via npm, build the project, and set environment variables (TC_API_TOKEN required, TC_API_URL optional, TC_DEFAULT_PROJECT optional). Configure the server in Claude Desktop, Claude Code, or Codex by specifying the command and environment. Start the server using npm run dev or npm start.

Key features of Testcollab Mcp Server

List test cases with filtering, sorting, and pagination
Create test cases with steps, tags, and custom fields
Update existing test cases (title, steps, priority, etc.)
Optional default project ID reduces repeated parameter input

Use cases of Testcollab Mcp Server

AI assistant queries and filters test cases in a TestCollab project
Create structured test cases with steps and expected results via natural language
Update test case details (priority, steps, tags) through conversational interface
Manage test cases across suites without direct UI interaction

FAQ from Testcollab Mcp Server

What configuration is required?

You must provide a TC_API_TOKEN from your TestCollab user profile. Optionally set TC_API_URL (default http://localhost:1337) and TC_DEFAULT_PROJECT to avoid specifying project_id each call.

How do I connect the server to an AI assistant?

Add the server configuration to Claude Desktop's claude_desktop_config.json or Claude Code's .claude/settings.json with the node command and environment variables. For Codex, use an HTTP endpoint with specific headers.

What tools are currently available?

The server provides list_test_cases, create_test_case, and update_test_case. Planned additions include delete, suite management, test plan management, and test execution recording.

Can I run this server locally for testing?

Yes. Use TC_API_TOKEN=your-token npm run dev for development with hot reload, or TC_API_TOKEN=your-token npm start for the built version. The server expects a running TestCollab instance at the configured API URL.

What is the default API URL and port?

The

开发工具分类下的更多 MCP 服务器

mcp-excalidraw

yctimlin

MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.

2.1K