Allows an AI agent to run Playwright test suites, identify flaky or slow tests, and debug failing tests through live step-by-step execution.
Also known as endformdev/skills, skills
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.83.2
- Last commit
- Nov 13, 2026
- License
- MIT
What is Endform MCP?
Endform allows an AI agent to run Playwright test suites, identify flaky or slow tests, and debug failing tests through live step-by-step execution.
Summary generated from the project's README
About Endform MCP server
Endform provides an MCP server that enables AI agents to manage and execute Playwright test suites. Developers can use this tool to identify flaky or slow tests and perform live step-by-step debugging of failing test steps. The server works by running the Endform CLI via npm, which transmits selected tests and their execution results to the Endform platform to facilitate parallel execution up to 10x faster than standard runs.
Integration is handled through various clients including Claude Code, Codex, VS Code, and Cursor. Users can install the skill via the Claude or Codex plugin marketplaces, use the skills.sh command for other agents, or manually add the MCP server using the npx command with stdio transport. Once connected, an agent can query test runs, quarantine problematic tests to prevent blocking pull requests, or investigate specific failures that only occur in CI environments.
What you can do with it
- 1Identify unstable testsAsk your agent to find which end-to-end tests are currently exhibiting flaky behavior.
- 2Debug CI failuresInstruct an AI to investigate a specific test that passes locally but fails during continuous integration.
- 3Manage test healthRequest that the agent quarantine a flaky test to ensure it does not interrupt the pull request process.
- 4Configure CI environmentsHave an agent set up the Endform infrastructure so that tests run on the platform during CI.
Written from the project's README. Every use case is checked against a quote from it.
How to install Endform MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Endform MCP in Claude Code
$ claude mcp add skills -- npx -y endformInstall Endform MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"skills": {
"command": "npx",
"args": [
"-y",
"endform"
]
}
}
}Install Endform MCP in VS Code
.vscode/mcp.json
{
"servers": {
"skills": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"endform"
]
}
}
}Install Endform MCP in VS Code CLI
$ code --add-mcp '{"name":"skills","type":"stdio","command":"npx","args":["-y","endform"]}'Install Endform MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"skills": {
"command": "npx",
"args": [
"-y",
"endform"
]
}
}
}Install Endform MCP in Codex
$ codex mcp add skills -- npx -y endformInstall Endform MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.skills] command = "npx" args = ["-y", "endform"]
Install Endform MCP in Gemini CLI
$ gemini mcp add -s user skills npx -- -y endformInstall Endform MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"skills": {
"command": "npx",
"args": [
"-y",
"endform"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachableendformdev/skills is public and reachablegithub.com/endformdev/skills ↗Pass
- Package names this repository as its sourceendform names git+https://github.com/endformdev/docs.git as its sourcenpmjs.com/package/endform ↗Finding
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/endformdev/skills ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from endformPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubEndform skills
Endform runs your existing Playwright suite in parallel, up to 10x faster, and helps you keep it healthy as it grows.
The endform skill lets your agent run your tests on Endform and find failing, flaky, and slow tests. It can then fix or quarantine them, or debug a test step by step in a live test.
Install
Claude Code
claude plugin marketplace add endformdev/skills
claude plugin install endform@endformdev
Claude Code doesn't update plugins from this marketplace automatically. To turn that on, run /plugin, go to Marketplaces, select endformdev, and select Enable auto-update. To update once, run claude plugin update endform@endformdev.
Codex
codex plugin marketplace add endformdev/skills
codex plugin add endform@endformdev
VS Code
In VS Code, enable chat.plugins.enabled, run Chat: Install Plugin From Source from the Command Palette, and enter https://github.com/endformdev/skills.
Other agents
Install the skill with skills.sh:
npx skills add endformdev/skills --skill endform
Pick your agents when prompted, or pass them with -a, for example -a claude-code. Add -g to install it for all your projects.
Use
Ask your agent, for example:
- "Set up Endform so our tests run on it in CI"
- "Which of our e2e tests are flaky?"
- "The checkout test only fails in CI, can you look into it?"
- "Quarantine the flaky search test so it stops blocking our PRs"
You can also call the skill directly: /endform in Claude Code and Cursor, /endform:endform in VS Code, and $endform in Codex.
MCP server
The Endform MCP server lets your agent query your test runs and debug failing tests on Endform. The Claude Code, Codex, and VS Code plugins add it for you.
To add it without the plugin, in Claude Code:
claude mcp add --transport stdio --scope local endform -- npx -y endform@latest mcp
For Cursor and other agents, see the MCP server docs.
Data and privacy
The plugin runs the Endform CLI from npm, which sends the Playwright tests you select, with what they need to run, and their results to Endform. See our privacy policy for more details.
Repository layout
skills/endform/SKILL.md The skill: when to use Endform and which reference to read
skills/endform/reference/ The reference the skill reads for each task: setup, CI, investigating tests, live tests
plugin.json Plugin manifest for Codex, GitHub Copilot, VS Code, and Cursor
mcp.json MCP server for those agents
.agents/plugins/ Marketplace for Codex
.claude-plugin/ Plugin and marketplace for Claude Code
.mcp.json MCP server for Claude Code
License
Endform MCP questions
How do I add Endform MCP to Claude Code?
Run claude mcp add skills -- npx -y endform in your terminal. Add --scope user to make it available in every project.
How do I add Endform MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can the Endform skill do with my tests?
It can run your tests, find failing, flaky, or slow tests, fix or quarantine them, and debug test steps in a live environment.
How does the plugin handle my data?
The plugin uses the Endform CLI to send selected Playwright tests, their necessary execution data, and results to Endform.
Can I use Endform to speed up my test suite?
Yes, Endform runs existing Playwright suites in parallel to increase speed by up to 10x.