Assert
About
Run real Playwright E2E tests from your AI coding agent — no Playwright knowledge required. Describe what to test in plain English, Assert writes and executes the test against your live app, and reports back step-by-step results.
Details
- Author
- Pixel-Funnel
- Downloads
- 370
- Categories
- Other, Developer Tools, Automation, AI
Jump to
- Connect AI agents (Claude, Cursor, Windsurf) to the Assert testing platform.
- Generate test scenarios from plain English descriptions.
- Run tests against live applications using Playwright.
- Receive pass/fail results with step-level details and screenshot URLs.
- No test code required.
- Free tier available at assert.click.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AssertCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the MCP server and configure it to use the provided tools: assert_list, assert_generate, assert_run, and assert_status. A free tier is available at assert.click. No Playwright knowledge is required.
assert_list
List existing E2E test scenarios saved in Assert. Use this to audit coverage before generating new tests. Supports filtering by project and pagination.
assert_generate
Generate a ready-to-run E2E test scenario in Assert Markdown format from a plain-English description. Optionally save it to Assert for later execution.
assert_run
Execute a test scenario and return a run ID. Accepts either a saved scenario_id or ad-hoc markdown. Runs are async — use assert_status to poll for completion.
assert_status
Poll a test run for its current status and step-level results. Returns pass/fail with actionable failure details and screenshot URLs for failed steps.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"assert": {
"assert": {
"command": "npx",
"args": [
"-y",
"@assert-click/mcp"
],
"env": {
"ASSERT_API_KEY": "your_api_key_here"
}
}
}
}
}McpServers
{
"assert": {
"command": "npx",
"args": [
"-y",
"@assert-click/mcp"
],
"env": {
"ASSERT_API_KEY": "your_api_key_here"
}
}
}Assert MCP connects your AI agent (Claude, Cursor, Windsurf) directly to the Assert testing platform. Generate test scenarios from plain English, run them against your live app using Playwright, and get pass/fail results with step-level details and screenshot URLs — all without writing a single line of test code.
Tools included:
- assert_list — list your saved test scenarios
- assert_generate — generate a test scenario from a description
- assert_run — execute a scenario or ad-hoc markdown test
- assert_status — poll a run for step-level results
Free tier available at https://assert.click. No Playwright knowledge required.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
