vision squeezer for LangChain
io.github.eralpozcan/vision-squeezer
Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen
client:LangChain
transport:stdio
runtime:npm
Install vision squeezer in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"vision-squeezer": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "vision-squeezer"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs