sift runs on your own machine — the client starts it, so there is no endpoint to ping. 73 installs a week from pypi. Last commit 11 Sep 2026.
Runs a command, keeps every byte on disk, returns only the lines that matter
What the code does
We read the source, 19 h ago · rules 995398eba69f
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.
proc = subprocess.Popen(
shell = True
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 sift -- uvx sift-cli{
"mcpServers": {
"sift": {
"command": "uvx",
"args": [
"sift-cli"
]
}
}
}[mcp_servers.sift]
command = "uvx"
args = ["sift-cli"]{
"mcpServers": {
"sift": {
"command": "uvx",
"args": [
"sift-cli"
]
}
}
}{
"servers": {
"sift": {
"type": "stdio",
"command": "uvx",
"args": [
"sift-cli"
]
}
}
}Optional settings from the registry entry, left out of the block above:
NVIDIA_API_KEY (A free NVIDIA NIM key. Optional: without one every tool still runs the command, still keeps every byte, and still returns the exit code -- what is lost is the model's choice of lines, not the output. Also read from ~/.config/nvidia/api_key).
Alternatives to sift
same job, measured the same wayAsk a repository what depends on what. Every answer cites the file, line and commit it came from.
Run commands on your remote test machines over SSH without the agent ever seeing a secret.
Live Google web search for AI agents that returns only the passages that answer the question.
Agent memory that keeps every correction, with history and as-of reads. Runs on your database.
Find the .rpy lines that compile clean and only break inside a player's save
Marks the lines in your test suite that current pytest no longer runs — and the config keys it silen
A tactile React component library, and the design system that keeps your AI agent on-brand.
Sophisticated bash command MCP server that runs and manages shell execution.
sift — questions
Answers built from our own checks of this server.