optlens runs on your own machine — the client starts it, so there is no endpoint to ping. 657 installs a week from pypi. Last commit 9 Oct 2026.
Debug and explain LP/MILP models: why infeasible, the smallest fix, what-if and sensitivity.
What the code does
We read the source, 2 d 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.
return fn(md.write_mps(os.path.join(tmp, f"{md.name or 'model'}.mps")))
exec(code, ns)
self.proc = subprocess.Popen([sys.executable, "-m", "optlens.workspace"], cwd=self.workdir, env=env,
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 optlens -- uvx optlens{
"mcpServers": {
"optlens": {
"args": [
"optlens"
],
"command": "uvx"
}
}
}[mcp_servers.optlens]
command = "uvx"
args = ["optlens"]{
"mcpServers": {
"optlens": {
"args": [
"optlens"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"optlens": {
"args": [
"optlens"
],
"command": "uvx"
}
}
}Alternatives to optlens
same job, measured the same wayMCP server and CLI that makes CSS legible to AI agents — explains what applies and why.
Finds the Git commits that explain why code is the way it is: semantic and full-text history search.
Find and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in.
Why can't I enable CONFIG_X? Explains Kconfig dependencies and finds a verified fix.
Inspect Mac and AI-tool storage, explain file activity, and clean safely with Trash and Undo.
Train, explain, optimise and deploy transparent glass-box ML models via workflow tools.
Debug kernels through QEMU's gdbstub with no gdb binary - and explain triple faults.
Live Ethereum whale flows: token activity, top tokens, latest moves, Whale Sentiment Index.
optlens — questions
Answers built from our own checks of this server.