Skip to content
mcp/harbor
LangChain

canvas mcp for LangChain

io.github.vishalsachdev/canvas-mcp

Canvas LMS integration for students and educators with optional privacy controls

client:LangChain transport:stdio runtime:pypi

Install canvas mcp in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "canvas-mcp": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["canvas-mcp"],
        }
})

tools = await client.get_tools()

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

canvas mcp in other clients

canvas mcp MCP server