cypress-mcp
MCP server that gives AI coding agents full control over Cypress test execution, allowing them to run, debug, and iterate on E2E tests directly from MCP-compatible agents.
README
cypress-mcp
MCP server that gives AI coding agents full control over Cypress test execution.
Run, debug, and iterate on E2E tests directly from Claude Code, Cursor, Windsurf, or any MCP-compatible agent — without switching to a terminal.
Install
| Package Manager | Command |
|---|---|
| npx (no install) | npx cypress-mcp --cwd /path/to/project |
| npm | npm install -g cypress-mcp |
| pnpm | pnpm add -g cypress-mcp |
| yarn | yarn global add cypress-mcp |
| bun | bun add -g cypress-mcp |
| From GitHub | npx github:jams4code/cypress-mcp |
Quick Start
Register with your MCP client:
Claude Code:
claude mcp add cypress-mcp -- npx cypress-mcp --cwd /path/to/project
Cursor / VS Code:
{
"mcpServers": {
"cypress": {
"command": "npx",
"args": ["cypress-mcp", "--cwd", "/path/to/your/project"]
}
}
}
Windsurf:
{
"mcpServers": {
"cypress": {
"command": "npx",
"args": ["cypress-mcp", "--cwd", "/path/to/your/project"]
}
}
}
Why
AI agents can write Cypress tests but can't run them. Every change requires you to switch to terminal, run npx cypress run, wait, copy the output back. This kills iteration speed.
cypress-mcp closes the loop. The agent runs specs, reads failures, views screenshots, inspects crash context, reruns the last command, and discovers the test suite — all within the conversation.
Tools (11)
Core Loop
| Tool | What it does |
|---|---|
cypress_run_spec |
Run a spec file headless, get structured JSON results |
cypress_run_test |
Run a single test by name (grep filter) |
cypress_rerun_last |
Replay the exact last run without rebuilding arguments |
cypress_list_specs |
List all spec files with test counts |
Debug
| Tool | What it does |
|---|---|
cypress_get_failure_context |
Compact debugging bundle: error, stack, spec excerpt, screenshots, next actions |
cypress_get_screenshot |
Find failure screenshots by spec or test name |
cypress_get_last_run |
Full results of the most recent run |
Discovery
| Tool | What it does |
|---|---|
cypress_discover |
Map the entire test suite: specs, test names, counts |
cypress_analyze_spec |
Deep-parse a spec: describe blocks, visits, intercepts, fixtures |
Setup
| Tool | What it does |
|---|---|
cypress_get_env |
Show cypress.env.json (secrets masked) |
cypress_doctor |
Health check: config, binary, specs, support file, directories |
How It Works
graph LR
A[AI Agent] -->|stdio JSON-RPC| B[cypress-mcp]
B -->|child_process.spawn| C[Cypress Runtime]
C -->|JSON reporter| B
B -->|structured result| A
style A fill:#1a1a2e,stroke:#e94560,color:#fff
style B fill:#16213e,stroke:#0f3460,color:#fff
style C fill:#0f3460,stroke:#533483,color:#fff
- stdio transport — the agent spawns the server as a child process
- Serial execution — one Cypress run at a time, no concurrency
- Structured output — JSON results with failure details, diffs, screenshot paths
- Config-aware — auto-detects
cypress.config.*, follows relative imports, respects custom paths - Cross-platform — Windows, macOS, Linux
Agent Workflow
graph TD
D[cypress_discover] -->|map test suite| E[cypress_analyze_spec]
E -->|understand spec| F[cypress_run_spec]
F -->|tests fail| G[cypress_get_failure_context]
G -->|error + excerpt + screenshots| H[Fix the code]
H -->|iterate| I[cypress_rerun_last]
I -->|still failing| G
I -->|passing| J[Done]
F -->|tests pass| J
style D fill:#1a1a2e,stroke:#e94560,color:#fff
style F fill:#16213e,stroke:#0f3460,color:#fff
style G fill:#e94560,stroke:#fff,color:#fff
style I fill:#0f3460,stroke:#533483,color:#fff
style J fill:#2d6a4f,stroke:#40916c,color:#fff
Configuration
Works out of the box for standard Cypress projects. For custom setups, create cypress-mcp.config.json:
{
"defaultBrowser": "chrome",
"defaultTimeout": 600000,
"cypressConfigFile": "config/cypress.config.ts",
"specPattern": ["e2e/**/*.cy.ts"],
"supportFile": "support/e2e.ts",
"titleFilterSupport": true,
"screenshotsDir": "cypress/screenshots"
}
Supported Versions
- Cypress 12.x — 15.x
- Node.js 18+
- Windows, macOS, Linux
Registry Status
| Registry | Package | Status |
|---|---|---|
| npm | cypress-mcp |
Published |
| GitHub | jams4code/cypress-mcp |
Source |
Development
git clone https://github.com/jams4code/cypress-mcp.git
cd cypress-mcp
npm install
npm run build
npm test
License
Business Source License 1.1 — free for individuals, education, and open source. Commercial production use requires a license. See LICENSING.md for details.
Converts to Apache 2.0 on March 25, 2029.
Licensed by JADEV GROUP SARL (BE1027.114.687), Brussels, Belgium.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。