Cypress MCP
Wire Cypress end-to-end testing into AI agents
BestMCPTools
Cypress MCP
bestmcptools.org
Last verified: September 20, 2026
Maintenance status
Repository link unavailableThe GitHub link we had for this server no longer resolves.
How to Install Cypress MCP
$npx -y @cypress/mcp-serverCompatible with: Claude, Claude Code, Cursor, VS Code.
Setup by client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"cypress-mcp": {
"command": "npx",
"args": [
"-y",
"@cypress/mcp-server"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"cypress-mcp": {
"command": "npx",
"args": [
"-y",
"@cypress/mcp-server"
]
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"cypress-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cypress/mcp-server"
]
}
}
}Claude Code (terminal)
claude mcp add cypress-mcp -- npx -y @cypress/mcp-serverAdd any API keys or environment variables the server's README lists.
About Cypress MCP
The Cypress MCP server connects the Cypress end-to-end testing platform to AI agents, letting them create, run, and inspect browser tests from a chat interface. Useful for AI-assisted test automation and debugging.
Cypress MCP is a Testing MCP server designed for developers and AI power users. It enables extending AI assistants with real-world capabilities by exposing a structured set of tools over the Model Context Protocol. Key capabilities include standards-based mcp server interface, works with claude, gpt, gemini, and other mcp clients, tool discovery and structured outputs, and structured tool calls that work cleanly inside an LLM context. It integrates with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client, and is best suited for developers and AI power users who need ai engineers wiring assistants into real tools.
Key Features
- testing
- automation
- e2e
- Standards-based MCP server interface
- Works with Claude, GPT, Gemini, and other MCP clients
- Tool discovery and structured outputs
Pricing
Free: from Free (open source; Cypress account for cloud features)
Pros & Cons
Pros
- Drop-in support across MCP-compatible AI clients
- Reduces prompt boilerplate by exposing concrete tool calls
- Active community and ongoing updates
Cons
- Requires an MCP-capable client to use
- Initial setup can require configuration
- Capability surface depends on what the underlying service exposes
Best For
- AI engineers wiring assistants into real tools
- Teams adopting MCP as an integration standard
- Power users who want more than chat
Our Take on Cypress MCP
The Cypress MCP wires Cypress's end-to-end testing platform into AI agents so they can generate, run, and debug tests conversationally. A strong fit for teams already invested in Cypress, with the hosted Cypress Cloud pieces tied to a paid account.