ember runs on your own machine — the client starts it, so there is no endpoint to ping. 3 381 installs a week from pypi. Last commit 11 Oct 2026.
Calibrated advice for coding agents: typed questions in, probabilities out. Apple Silicon.
What the code does
We read the source, 4 h ago · rules ccca72095570
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.
command = subprocess.run( # noqa: S603
env = dict(os.environ)
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 ember -- uvx ember-advise{
"mcpServers": {
"ember": {
"args": [
"ember-advise"
],
"command": "uvx"
}
}
}[mcp_servers.ember]
command = "uvx"
args = ["ember-advise"]{
"mcpServers": {
"ember": {
"args": [
"ember-advise"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"ember": {
"args": [
"ember-advise"
],
"command": "uvx"
}
}
}This one needs environment variables set before it will start:
EMBER_SERVER_URL (Inference endpoint; defaults to the local model server at http://127.0.0.1:8765), EMBER_AUTH_TOKEN (Credential for a remote inference endpoint).
The author declared them in the registry entry; get the values from the project itself.
Alternatives to ember
same job, measured the same wayCalibrated decisions for agents: choice, yes/no and score questions answered with probabilities.
MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
TypeScript inferred types, completions and type errors for AI coding agents
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
Local gut check before risky agent actions: calibrated safe/intended probabilities, no API calls.
On-brand image generation (product shots, app icons, OG cards, sprites) for AI coding agents.
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
TypeScript inferred types, completions and type errors for AI coding agents
ember — questions
Answers built from our own checks of this server.