
Let your agent run and maintain your Playwright tests on Endform.
Let your agent run and maintain your Playwright tests on Endform.
·
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.
claude plugin marketplace add endformdev/skills
claude plugin install endform@endformdevClaude 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 plugin marketplace add endformdev/skills
codex plugin add endform@endformdevIn VS Code, enable chat.plugins.enabled, run Chat: Install Plugin From Source from the Command Palette, and enter https://github.com/endformdev/skills.
Install the skill with skills.sh:
npx skills add endformdev/skills --skill endformPick your agents when prompted, or pass them with -a, for example -a claude-code. Add -g to install it for all your projects.
Ask your agent, for example:
You can also call the skill directly: /endform in Claude Code and Cursor, /endform:endform in VS Code, and $endform in Codex.
The Endform MCP server lets your agent query your test runs and debug failing tests on Endform. It comes in two versions:
| Local | Remote | |
|---|---|---|
| Runs | On your machine, through npx | On Endform, at https://endform.dev/mcp |
| Best for | Coding agents working in your repository | Agents that can't run local commands, such as claude.ai |
| Sign-in | npx endform@latest login or ENDFORM_API_KEY | Your Endform account, in the browser |
| Organizations | Any you can access | All of yours, or one you choose when you connect |
| Live test debugging | Yes | No, it needs your local checkout |
The Codex and VS Code plugins add it for you. To add it in Claude Code:
claude mcp add --transport stdio --scope local endform -- npx -y endform@latest mcpFor Cursor and other agents, see the MCP server docs.
Add https://endform.dev/mcp as a remote MCP server in your agent and sign in with your Endform account. You choose all your organizations or a single one when you connect.
The Claude Code plugin adds it for you: run /mcp to sign in. To add it without the plugin, in Claude Code, add it and then run /mcp:
claude mcp add --transport http endform-remote https://endform.dev/mcpIn Codex:
codex mcp add endform-remote --url https://endform.dev/mcp
codex mcp login endform-remoteIn VS Code, add this to .vscode/mcp.json and sign in when prompted:
{
"servers": {
"endform-remote": {
"type": "http",
"url": "https://endform.dev/mcp"
}
}
}If you use the local server in one agent and the remote server in another, there's nothing else to set up: each agent has its own connection.
You can also add both to one agent by giving them different names, as the commands above do. It's usually better to pick one: local if the agent can run commands, remote if it can't.
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.
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 CodePick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add endform-remote --transport http https://endform.dev/mcp{
"mcpServers": {
"endform-remote": {
"url": "https://endform.dev/mcp",
"type": "http"
}
}
}code --add-mcp '{"name":"endform-remote","url":"https://endform.dev/mcp","type":"http"}'Runs as a hosted service. Your client connects over the network and nothing is installed locally.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/endform-skills to learn what the "Endform skills" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx skills add endformdev/skills --skill endformclaude mcp add --transport stdio --scope local endform -- npx -y endform@latest mcp
claude mcp add --transport http endform-remote https://endform.dev/mcpThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: its endpoint did not list its tools to an anonymous client, which usually means it asks for an API key or a sign-in. The four checks that need a live server are left out, and the grade tops out at B until we can read its tools.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/endform-skills)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "endform-skills" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.