Recovery Probe runs on your own machine — the client starts it, so there is no endpoint to ping. 1 007 installs a week from npm. Last commit 28 Oct 2026.
Fail reads in web and Electron test apps, inspect recovery, and compare before/after evidence.
We read the source, 4 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
const child = spawn(process.execPath, [cli, ...argv], {
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.
execFile(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 recovery-probe -- npx -y recovery-probe
{
"mcpServers": {
"recovery-probe": {
"command": "npx",
"args": [
"-y",
"recovery-probe"
]
}
}
}
[mcp_servers.recovery-probe]
command = "npx"
args = ["-y", "recovery-probe"]
{
"mcpServers": {
"recovery-probe": {
"command": "npx",
"args": [
"-y",
"recovery-probe"
]
}
}
}
{
"servers": {
"recovery-probe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"recovery-probe"
]
}
}
}
Run plain-English web QA tests and inspect check results and evidence.
Agentic UX testing for real Electron apps: launch, inspect, interact, and assert through MCP.
Test a web app in a real browser from plain English. Passed, failed or cannot verify, with evidence.
Generates unit tests for Python code with coverage before/after reports and concrete edge cases.
Read-only audit evidence for security, tests, native coverage, runtime failures and repair status.
Browser-backed QA with evidence and fix-ready reports for coding agents.
Inspect AI projects, traces, tests, and governance rules in Openlayer, and debug failing evals.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Answers built from our own checks of this server.