Run LLM eval suites on local or hosted models; compare runs with intervals and a noise floor.
Connect Runs on your machine
claude mcp add evalpair -e EVALPAIR_HOME=<EVALPAIR_HOME> -e EVALPAIR_API_KEY=<EVALPAIR_API_KEY> -- uvx evalpair==0.1.1
{
"mcpServers": {
"evalpair": {
"command": "uvx",
"args": [
"evalpair==0.1.1"
],
"env": {
"EVALPAIR_HOME": "<EVALPAIR_HOME>",
"EVALPAIR_API_KEY": "<EVALPAIR_API_KEY>"
}
}
}
}
{
"mcpServers": {
"evalpair": {
"command": "uvx",
"args": [
"evalpair==0.1.1"
],
"env": {
"EVALPAIR_HOME": "<EVALPAIR_HOME>",
"EVALPAIR_API_KEY": "<EVALPAIR_API_KEY>"
}
}
}
}
{
"servers": {
"evalpair": {
"type": "stdio",
"command": "uvx",
"args": [
"evalpair==0.1.1"
],
"env": {
"EVALPAIR_HOME": "<EVALPAIR_HOME>",
"EVALPAIR_API_KEY": "<EVALPAIR_API_KEY>"
}
}
}
}
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
EVALPAIR_HOMEOptional | Folder for the call cache, saved runs and your own suites (default ~/.evalpair). |
EVALPAIR_API_KEYOptional, secret | Bearer token for an OpenAI-compatible server, if it needs one (OPENAI_API_KEY also works). |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 5 Nov 2026 |
| Last updated | 5 Nov 2026 |
| Registry name | io.github.Srikarmk/evalpair |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
