All servers / Developer / Cypress MCP server
Cypress MCP server
MCP server for AI-driven Cypress test execution. Run, debug, and iterate on E2E tests from your AI agent, with Cypress Cloud recording and flaky test detection.
Tested by ConnectATDScore 90 out of 100. Tested 2026-11-18 on package version 0.2.1. Package: cypress-mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (2.5 seconds including download)
- Tools offered: 12
- Last published: 2026-11-17
- Weekly downloads (npm): 1,548
- License: Apache-2.0 · Direct dependencies: 4
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
cypress_discoverno parametersDiscover and map the entire Cypress test suite. Returns all specs with test counts, describe blocks, and test names. Use this first to understand what tests exist before writing or running anything.
cypress_analyze_spec1 of 1 parameter describedDeep analysis of a single spec file. Extracts describe/it blocks with line numbers, cy.visit URLs, cy.intercept routes, fixtures used, and custom commands called.
cypress_list_specs1 of 1 parameter describedList all Cypress spec files in the project. Returns file paths and test counts.
cypress_run_spec9 of 9 parameters describedRun a single Cypress spec file headless. Returns structured results with pass/fail/flaky counts, failure details, screenshot paths, the Cypress Cloud run URL when recorded, and recommended next actions.
cypress_run_test10 of 10 parameters describedRun a specific test by name within a spec file using grep (@cypress/grep). Returns structured results with recommended next actions for the agent.
cypress_rerun_lastno parametersReplay the exact last run_spec or run_test invocation, including its Cypress Cloud recording options. Removes friction when iterating on the same failure: no need to reconstruct arguments.
cypress_get_last_runno parametersReturn the full structured results of the most recent Cypress test run including runId, args used, and all test details.
cypress_get_failure_contextno parametersGet a compact debugging bundle for the most recent failure. Returns the failing test, error, stack hint, screenshot paths, relevant spec excerpt, and recommended next actions. This is the key tool for the fix-and-rerun loop.
cypress_get_screenshot2 of 2 parameters describedFind screenshot files from Cypress test failures. Returns absolute file paths that multimodal AI agents can read directly.
cypress_get_configno parametersReturn the resolved cypress-mcp configuration: project root, Cypress config file, browser, timeout, spec pattern, directories, and Cypress Cloud status (projectId, whether a record key is set). Use the projectId with Cypress Cloud MCP tools.
cypress_get_envno parametersReturn the contents of cypress.env.json with sensitive values masked. Safe to display.
cypress_doctorno parametersComprehensive health check of the Cypress project. Validates config file, binary, spec files, support file, and directories. Use this to diagnose setup issues.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.