TokenMark runs on your own machine — the client starts it, so there is no endpoint to ping. 417 installs a week from npm. Last commit 10 Oct 2026.
Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.
What the code does
We read the source, 3 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.
const p = spawn(bin, args, { stdio: "ignore", detached: 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 tokenmark-mcp -- npx -y @altronis/tokenmark-mcp{
"mcpServers": {
"tokenmark-mcp": {
"args": [
"-y",
"@altronis/tokenmark-mcp"
],
"command": "npx"
}
}
}[mcp_servers.tokenmark-mcp]
command = "npx"
args = ["-y", "@altronis/tokenmark-mcp"]{
"mcpServers": {
"tokenmark-mcp": {
"args": [
"-y",
"@altronis/tokenmark-mcp"
],
"command": "npx"
}
}
}{
"mcpServers": {
"tokenmark-mcp": {
"args": [
"-y",
"@altronis/tokenmark-mcp"
],
"command": "npx"
}
}
}Alternatives to TokenMark
same job, measured the same wayBenchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Local-first personal memory and model server for trusted MCP agents on macOS.
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
Hardware probe for performance diagnostics, thermal monitoring, and LLM optimization.
Report CPU, memory, disk, network, GPU and process information for local or remote nodes.
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
TokenMark — questions
Answers built from our own checks of this server.