Lastest runs on your own machine — the client starts it, so there is no endpoint to ping. 37 installs a week from npm. Last commit 10 Sep 2026.
Run visual regression tests, review diffs, and manage baselines on a Lastest instance.
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
new Function(body);
return execSync(`git ${cmd}`, { encoding: "utf-8" }).trim();
const filePath = path.join(tmpDir, safeName);
{onDelete &&
regions.map((r) => {
const leftPct = ((r.x + r.width) / dims.width) * 100;
ENV LASTEST_API_KEY=introspection-only
placeholder="https://hooks.slack.com/services/..."
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add lastest -- npx -y @lastest/mcp-server
{
"mcpServers": {
"lastest": {
"args": [
"-y",
"@lastest/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.lastest]
command = "npx"
args = ["-y", "@lastest/mcp-server"]
{
"mcpServers": {
"lastest": {
"args": [
"-y",
"@lastest/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"lastest": {
"args": [
"-y",
"@lastest/mcp-server"
],
"command": "npx"
}
}
}
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.
Manage test suites, run tests, view results, and automate QA workflows via AI with testRigor.
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Local-first visual regression for AI agents: verdicts, diff images, explain_snapshot. No API key.
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Hosted MCP for Pagent: review Bayesian A/B tests, capture hypotheses, manage websites via OAuth.
Create, manage, and test business rules directly from your AI agent via the DecisionRules platform.
Answers built from our own checks of this server.