Tesults MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 72 installs a week from npm. Last commit 18 Oct 2026.
Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.
Nothing serious here today
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.
Connect this server
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 -e 'TESULTS_API_TOKEN=<TESULTS_API_TOKEN>' -- npx -y tesults-mcp{
"mcpServers": {
"tesults-mcp": {
"command": "npx",
"args": [
"-y",
"tesults-mcp"
],
"env": {
"TESULTS_API_TOKEN": "<TESULTS_API_TOKEN>"
}
}
}
}[mcp_servers.tesults-mcp]
command = "npx"
args = ["-y", "tesults-mcp"]
env = { TESULTS_API_TOKEN = "<TESULTS_API_TOKEN>" }{
"mcpServers": {
"tesults-mcp": {
"command": "npx",
"args": [
"-y",
"tesults-mcp"
],
"env": {
"TESULTS_API_TOKEN": "<TESULTS_API_TOKEN>"
}
}
}
}{
"servers": {
"tesults-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tesults-mcp"
],
"env": {
"TESULTS_API_TOKEN": "<TESULTS_API_TOKEN>"
}
}
}
}Put your own value in place of
<TESULTS_API_TOKEN> (Tesults API token - obtain from your Tesults project configuration).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
TESULTS_READ_ONLY (Set to true for reporting-only mode: only the reporting and insight tools are exposed and non-GET API requests are blocked locally).
Alternatives to Tesults MCP
same job, measured the same wayRun Playwright tests and surface structured results for AI agents doing test failure analysis.
Create and manage test cases, test runs and results in Testiny from your AI assistant.
Run visual regression tests, review diffs, and manage baselines on a Lastest instance.
AI support agent on Zealoop: knowledge, procedures, actions, widget install and testing.
AI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
Runs Foundry tests and builds; returns compact, structured failures to AI coding agents
Crash-test your AI agent on real professional decisions, graded against what actually happened.
Test ideas, messages and ads with Human Digital Twins built from real people, in your AI assistant.
Tesults MCP — questions
Answers built from our own checks of this server.