Tesults MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 25 installs a week from npm. Last commit 10 May 2026.
Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.
Today is the operative word: we check Tesults MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 tesults-mcp -- npx -y tesults-mcp
{
"mcpServers": {
"tesults-mcp": {
"args": [
"-y",
"tesults-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.tesults-mcp]
command = "npx"
args = ["-y", "tesults-mcp"]
{
"mcpServers": {
"tesults-mcp": {
"args": [
"-y",
"tesults-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"tesults-mcp": {
"args": [
"-y",
"tesults-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
TESULTS_API_TOKEN (Tesults API token - obtain from your Tesults project configuration).
The author declared them in the registry entry; get the values from the project itself.
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
Run visual regression tests, review diffs, and manage baselines on a Lastest instance.
Ask about Cannon VoIP pricing, plans, features, international rates, coverage, and FAQs.
BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Test generation, mocks, coverage analysis for AI agents
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
Answers built from our own checks of this server.