Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.
Connect Runs on your machine
claude mcp add crit -- uvx crit==0.17.2
{
"mcpServers": {
"crit": {
"command": "uvx",
"args": [
"crit==0.17.2"
]
}
}
}
{
"mcpServers": {
"crit": {
"command": "uvx",
"args": [
"crit==0.17.2"
]
}
}
}
{
"servers": {
"crit": {
"type": "stdio",
"command": "uvx",
"args": [
"crit==0.17.2"
]
}
}
}
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 9 Nov 2026 |
| Last updated | 9 Nov 2026 |
| Registry name | io.github.crit-labs/crit |
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.
