Entroly runs on your own machine — the client starts it, so there is no endpoint to ping. 1 486 installs a week from pypi. Last commit 16 Sep 2026.
Context Assurance for AI agents: context engineering, AI cost optimization, verification.
We read the source, 23 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
completed = subprocess.run(
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
pattern: "chmod 777",
proc = subprocess.Popen(proxy_cmd, stdout=log_fh, stderr=subprocess.STDOUT)
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.
if os.environ.get("ENTROLY_NO_DOCKER") or os.path.exists("/.dockerenv"):
try { fs.unlinkSync(path.join(this.checkpointDir, old)); } catch {}
result = subprocess.run([str(candidate), *sys.argv[1:]], check=False)
const result = spawnSync(process.execPath, [target, ...process.argv.slice(2)], {
result = eval( # noqa: S307
process = new ProcessBuilder(executable, "--version")
API_BASE = "https://api.telegram.org/bot{token}/{method}"
env = dict(os.environ)
count = sum(1 for _ in checkpoint_dir.rglob("*") if _.is_file())
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 entroly -- npx -y entroly-mcp
{
"mcpServers": {
"entroly": {
"args": [
"-y",
"entroly-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.entroly]
command = "npx"
args = ["-y", "entroly-mcp"]
{
"mcpServers": {
"entroly": {
"args": [
"-y",
"entroly-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"entroly": {
"args": [
"-y",
"entroly-mcp"
],
"command": "npx"
}
}
}
Temporal engineering context for agents via MCP.
Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.
Agent reasoning, memory, and token-optimized context for AI applications.
Memory, docs, and repo context layer for engineering agents.
Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
Evidence-gated verification, selection, and measurement MCP for coding agents.
Context engineering for AI coding agents: product context, project missions, and 360 memory.
Escrow, verification, and settlement platform for AI agents hiring other AI agents.
Answers built from our own checks of this server.