Alchemite MCP runs on your own machine — the client starts it, so there is no endpoint to ping.
Train and use Alchemite machine learning models for experimental design in your local agent.
Today is the operative word: we check Alchemite MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 alchemite-mcp -- uvx alchemite-mcp
{
"mcpServers": {
"alchemite-mcp": {
"args": [
"alchemite-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.alchemite-mcp]
command = "uvx"
args = ["alchemite-mcp"]
{
"mcpServers": {
"alchemite-mcp": {
"args": [
"alchemite-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"alchemite-mcp": {
"args": [
"alchemite-mcp"
],
"command": "uvx"
}
}
}
GPU-accelerated MCP server for neural network training, deep learning, and model experimentation
MCP server for Callimachus: local index and search of your AI coding-agent threads
Manage your local model machine over MCP: state, model pull/remove, service switch, LoRA training
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
Local design engine for AI agents: create, edit and export real, editable designs.
Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.
A/B testing for vibe coders: create, track, and ship experiments from your AI coding agent.
Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Answers built from our own checks of this server.