Greenrun MCP Server

@Add-Item-To

代码仓库主页

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

Add-Item-To

提交者

Stewis

关于 Greenrun MCP Server

Browser test management for Claude Code. Write tests in plain English, run them with /greenrun.

#browser-testing#claude-code #playwright#e2e-testing#natural-language #mcp #testing

Greenrun MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "greenrun": {
      "command": "npx",
      "args": [
        "greenrun-cli"
      ]
    }
  }
}

Greenrun MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Greenrun?

Greenrun is an MCP server that connects Claude Code to the Greenrun API for browser test management. You describe tests in plain English, and Claude generates and runs Playwright scripts automatically, handling script generation, parallel execution, result tracking, and re-running only what's needed.

How to use Greenrun?

Run npx greenrun-cli init to launch an interactive setup wizard that validates your API token, configures the Greenrun and Playwright MCP servers, installs slash commands, and adds project instructions. Tests are defined in the Greenrun dashboard or via MCP tools, then executed by running /greenrun in Claude Code. Manual setup is also supported via claude mcp add or .mcp.json.

Key features of Greenrun

Write tests in plain English, no Playwright code needed
Claude generates Playwright scripts on first run
Cached scripts skip generation on subsequent runs
Parallel test execution with result tracking
Impact analysis via /greenrun-sweep for changed pages
Named credential sets for authentication per test
Test filtering by tag, URL path, or name

Use cases of Greenrun

Define and run end-to-end browser tests without writing code
Quickly re-run only the tests affected by recent code changes
Manage test suites across multiple projects with credential management
Integrate browser testing directly into Claude Code workflows

常见问题

What are the prerequisites for using Greenrun?

Node.js 18+, Claude Code, and the Playwright MCP server (configured automatically by the init wizard).

How does Greenrun generate test scripts?

On the first run, Claude walks through each test's instructions in the browser, observes UI states, and generates a `.spec.ts` script with real selectors. The script is cached and reused on future runs.

How does Greenrun handle test failures due to stale scripts?

If a cached script fails, an AI agent re-executes the test manually to determine whether the script is stale or there is a real bug. Stale scripts are automatically cleared for regeneration.

How does Greenrun handle authentication?

Projects support named credential sets (name, email, password). Each test can reference a credential by name via `credential_name`, and during execution the matching credentials are used to authenticate.

How can I run only tests affected by recent code changes?

Run the `/greenrun-sweep` slash command. It detects which tests are impacted by the pages you changed (based on git changes) and offers to run only those tests.

开发工具分类下的更多 MCP 服务器

FARPY

mangomunchr

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

bofob

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

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.