Skip to content
mcp/harbor
LangChain

openeye for LangChain

io.github.dumbspacecookie/openeye

Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.

client:LangChain transport:stdio runtime:npm

Install openeye in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "openeye": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "@dumbspacecookie/openeye"],
        }
})

tools = await client.get_tools()

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

openeye in other clients

openeye MCP server