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.
@TCSoftInc
基本情報
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
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"testcollab": {
"url": "https://mcp.testcollab.io/mcp",
"transport": "sse"
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
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.
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.
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.
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.
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.
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.
The

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac
コメント