Distil runs on your own machine — the client starts it, so there is no endpoint to ping. 1 624 installs a week from pypi. Last commit 18 Sep 2026.
Reversibly compress tool outputs to recoverable handles; expand to exact original bytes on demand.
What the code does
We read the source, 9 h ago · rules 3dff92dd89df
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.
setup.py: выполняет код при установке пакета
proc = subprocess.run(
const child = spawn(runner.cmd, args, { stdio: "inherit" });
lib_dir = os.path.join(fw_prefix, 'Python.framework', 'Versions', ver, 'lib')
rc = subprocess.run(cmd, shell=True).returncode
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 distil -- uvx distil-llm{
"mcpServers": {
"distil": {
"args": [
"distil-llm"
],
"command": "uvx"
}
}
}[mcp_servers.distil]
command = "uvx"
args = ["distil-llm"]{
"mcpServers": {
"distil": {
"args": [
"distil-llm"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"distil": {
"args": [
"distil-llm"
],
"command": "uvx"
}
}
}Alternatives to Distil
same job, measured the same wayReversible context compression for AI agents: cut token usage up to 94%, originals retrievable
Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads
Resolve Geepers physical handles to exact coordinates + navigation for AI agents.
Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
On-demand access to amCharts 5 docs, code examples, and API reference
AI-optimized tool output compression for read, grep, diff, bash, test, web, search, and more
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
Local-first PDF tools for AI agents: merge, split, extract, render, compress. Files stay on-device.
Distil — questions
Answers built from our own checks of this server.