4q Tokenz runs on your own machine — the client starts it, so there is no endpoint to ping. 90 installs a week from npm. Last commit 21 Oct 2026.
Intelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call.
What the code does
We read the source, 6 d 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.
пакет 4q-tokenz ссылается на steveweltman/4q-tokenz
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 4q-tokenz -- npx -y 4q-tokenz{
"mcpServers": {
"4q-tokenz": {
"command": "npx",
"args": [
"-y",
"4q-tokenz"
]
}
}
}[mcp_servers.4q-tokenz]
command = "npx"
args = ["-y", "4q-tokenz"]{
"mcpServers": {
"4q-tokenz": {
"command": "npx",
"args": [
"-y",
"4q-tokenz"
]
}
}
}{
"servers": {
"4q-tokenz": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"4q-tokenz"
]
}
}
}Alternatives to 4q Tokenz
same job, measured the same wayStateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
Incident management, on-call scheduling, and intelligent analysis powered by Rootly.
Pre-computed market data that improves agent reasoning, reduces token usage, and replaces pipelines.
Read-only MCP server for UK gym search using the LocalGym Agent API.
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
Search and read a patient chart over the Canvas FHIR R4 API. Read-only.
Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status.
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
4q Tokenz — questions
Answers built from our own checks of this server.