Vision Squeezer runs on your own machine — the client starts it, so there is no endpoint to ping. 416 installs a week from npm. Last commit 23 Oct 2026.
Shrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.
What the code does
We read the source, 1 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.
postinstall: node postinstall.js
const r = spawnSync(bin, args, { encoding: 'utf8', timeout: 30000, windowsHide: 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 vision-squeezer -- npx -y vision-squeezer{
"mcpServers": {
"vision-squeezer": {
"command": "npx",
"args": [
"-y",
"vision-squeezer"
]
}
}
}[mcp_servers.vision-squeezer]
command = "npx"
args = ["-y", "vision-squeezer"]{
"mcpServers": {
"vision-squeezer": {
"command": "npx",
"args": [
"-y",
"vision-squeezer"
]
}
}
}{
"servers": {
"vision-squeezer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vision-squeezer"
]
}
}
}Alternatives to Vision Squeezer
same job, measured the same wayImage & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
Token and context budget for AI agents. Tracks spend and gates the session.
Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Verify signed AIFeed permissions, fetch token-budgeted markdown, and verify assets for AI agents.
Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows.
Hosted MCP: search, fetch, compress, dedup, budget, memory, pipelines. Not an LLM proxy.
Fetch public web pages as clean, token-budgeted text for AI agents.
Vision Squeezer — questions
Answers built from our own checks of this server.