Tesults MCP

Name: Tesults MCP
Author: tesults

@tesults

Repository

About Tesults MCP

Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.

#testing #test-automation #playwright #jest #pytest #cypress #ci-cd #reporting #developer-tools

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "tesults": {
      "command": "npx",
      "args": [
        "tesults-mcp"
      ],
      "env": {
        "TESULTS_API_TOKEN": "<YOUR_TOKEN>"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Tesults MCP?

Tesults MCP connects AI agents to your test automation results, enabling plain-language analysis of test failures and regressions. Designed for developers and QA engineers, it works with popular testing frameworks like Playwright, Jest, Pytest, Cypress, and JUnit.

How to use Tesults MCP?

Set the TESULTS_API_TOKEN environment variable with your Tesults API token, then invoke the server to let your AI agent query test results for failures, regressions, and run comparisons.

Key features of Tesults MCP

Identify regressions and what's resolved or continuing to fail.
Compare test runs to see what changed.
Get plain-language explanations of test failures.
Works with Playwright, Jest, Pytest, Cypress, JUnit and more.

Use cases of Tesults MCP

Ask an AI agent why specific tests are failing in a CI pipeline.
Automatically surface regressions across multiple test runs.
Compare current and previous test results to diagnose trends.

FAQ from Tesults MCP

How do I set up Tesults MCP?

Set the TESULTS_API_TOKEN environment variable with your Tesults API token.

Which testing frameworks does Tesults MCP support?

It works with Playwright, Jest, Pytest, Cypress, JUnit, and more.

What can I ask the AI agent about my test results?

You can ask for plain-language explanations of failures, identification of regressions, what issues are resolved or continuing to fail, and comparisons between runs.