Alchemite MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 227 installs a week from pypi.
Design experiments and make predictions for materials & chemicals properties 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": {
"command": "uvx",
"args": [
"alchemite-mcp"
]
}
}
}
[mcp_servers.alchemite-mcp]
command = "uvx"
args = ["alchemite-mcp"]
{
"mcpServers": {
"alchemite-mcp": {
"command": "uvx",
"args": [
"alchemite-mcp"
]
}
}
}
{
"servers": {
"alchemite-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"alchemite-mcp"
]
}
}
}
Design tool for agents: draw, edit and check designs in files your team edits and comments on.
Local design engine for AI agents: create, edit and export real, editable designs.
Local mandate gate and proof trail for AI agents that take consequential actions.
MCP server for NOAA tides and currents predictions and water levels.
Read and update your Vara lab experiments, runs, daily plans, references and materials.
Read and update your Vara lab experiments, runs, daily plans, references and materials.
Semilattice lets agents make predictions about audiences for content testing and decision making.
Prediction markets, on-chain flows, ETF flows, equities and macro intelligence for AI agents.
Answers built from our own checks of this server.