Skip to content
LangChain

Visual Memory MCP for LangChain

io.github.putervision/vision-memory-mcp

Local visual UI cache for AI agents using perceptual hashing + CLIP to cut vision token use.

client:LangChain transport:stdio runtime:npm

Install Visual Memory MCP in LangChain

pip install langchain-mcp-adapters

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "vision-memory-mcp": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "@putervision/vision-memory-mcp"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

Visual Memory MCP in other clients