visual intent layer for LangChain
io.github.willa-code/visual-intent-layer
Point at visible targets in an agent-built interface, and deliver grounded Annotations.
client:LangChain
transport:stdio
runtime:npm
Install visual intent layer in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"visual-intent-layer": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "visual-intent-layer"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs