Token Optimizer MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 821 installs a week from npm. Last commit 19 Sep 2026.
Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.
We read the source, 4 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
const child = spawn(
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
(step.run.includes('sudo') || step.run.includes('chmod 777'))
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.
postinstall: node scripts/postinstall.cjs
const result = spawnSync(
return pathToFileURL(path.join(here, '..', '..', 'hooks-core', name)).href;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 token-optimizer-mcp -- npx -y @ooples/token-optimizer-mcp
{
"mcpServers": {
"token-optimizer-mcp": {
"args": [
"-y",
"@ooples/token-optimizer-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.token-optimizer-mcp]
command = "npx"
args = ["-y", "@ooples/token-optimizer-mcp"]
{
"mcpServers": {
"token-optimizer-mcp": {
"args": [
"-y",
"@ooples/token-optimizer-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"token-optimizer-mcp": {
"args": [
"-y",
"@ooples/token-optimizer-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
TOKEN_OPTIMIZER_CACHE_DIR (Directory path for cache storage (optional, defaults to ~/.token-optimizer-mcp)).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Skim code transformation. Compresses code 60-95% for LLM context optimization.
MCP server that cuts AI coding agent token usage via framework-aware context optimization
Compress images to target sizes (80%+ smaller). Tools: compress_image, convert_image, optimize_image
MCP Server for SlimContext - AI chat history compression tools
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
What fills your agent's context window before a session starts: skill descriptions, memory files.
Compress PDFs to exact target sizes (82-93% smaller). Tools: compress_pdf, optimize_pdf, inspect_pdf
Answers built from our own checks of this server.