mcp knowledge gaps for LangChain
io.github.onetrueclaude-creator/mcp-knowledge-gaps
Find what your knowledge base mentions but doesn't actually explain.
client:LangChain
transport:stdio
runtime:pypi
Install mcp knowledge gaps in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"mcp-knowledge-gaps": {
"transport": "stdio",
"command": "uvx",
"args": ["mcp-knowledge-gaps"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs