Epistemic Integrity Framework (EIF) for LangChain
io.github.leocelis/eif
Runtime gate for AI agent claims. Catches sycophantic drift, circular self-validation, causal errors
client:LangChain
transport:sse
Install Epistemic Integrity Framework (EIF) in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"eif": {
"transport": "streamable_http",
"url": "https://eif.leocelis.com/sse",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs