Calibration Explorer runs on your own machine — the client starts it, so there is no endpoint to ping. 20 installs a week from npm. Last commit 5 Oct 2026.
Check classifier confidence against accuracy, fit temperature scaling and save local reports.
What the code does
We read the source, 4 d ago · rules 995398eba69f
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.
… : ""}>${n.toLocaleString("en-US")}</option>`).join("")}</select></label>${logitExample ? `<label>Confidence distortion<select id="learning-distortion">${distortionValues.map((value) => `<option value="${value}" ${value === options.distortion ? "selected" : ""}>${h(value)}×</opt…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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 calibration-explorer -- npx -y @m-sanchez/calibration-explorer-mcp{
"mcpServers": {
"calibration-explorer": {
"command": "npx",
"args": [
"-y",
"@m-sanchez/calibration-explorer-mcp"
]
}
}
}[mcp_servers.calibration-explorer]
command = "npx"
args = ["-y", "@m-sanchez/calibration-explorer-mcp"]{
"mcpServers": {
"calibration-explorer": {
"command": "npx",
"args": [
"-y",
"@m-sanchez/calibration-explorer-mcp"
]
}
}
}{
"servers": {
"calibration-explorer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@m-sanchez/calibration-explorer-mcp"
]
}
}
}Alternatives to Calibration Explorer
same job, measured the same wayLocal QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports.
AI Incident Reporting Compliance MCP. Unified classification + reporting-clock tracker across EU...
Local-first, read-only ECZ-ID verifier over MCP (stdio): checks, reports, explains, routes.
Local code validation with explicit execution trust and evidence of what actually ran.
Verified statistics for AI agents: guided tests, A/B tests, Tukey HSD, reports, optional Jev checks.
FMCSA motor-carrier risk scores, monitoring, and carrier-selection evidence reports for AI agents.
Checks the context files a coding agent reads against the git index, and reports what drifted.
Calibration Explorer — questions
Answers built from our own checks of this server.