Neumann for LangChain
io.github.kromatic-innovation/neumann
Monte Carlo ranges for uncertain plans: project cost, budget, timeline, capacity, NPV/IRR/payback.
client:LangChain
transport:streamable-http
tools:17
Install Neumann in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"neumann": {
"transport": "streamable_http",
"url": "https://neumann.kromatic.com/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs
What LangChain can do once it is connected
- run_monte_carlo_simulation
- rank_inputs_by_impact
- summarize_outcome_scenarios
- check_simulation_model
- estimate_simulation_size_and_cost
- convert_range_to_distribution
- convert_distribution_to_range
- get_simulation_results
- check_account_and_credits
- send_feedback
- buy_credits
- create_result_share_link
- save_graph
- list_graphs
- get_graph
- delete_graph
- delete_run