KumoRFM is a pre-trained Relational Foundation Model (RFM) that generates training-free predictions on any relational multi-table data by interpreting the data as a (temporal) heterogeneous graph. It can be queried via the Predictive Query Language (PQL).
This repository hosts a full-featured MCP (Model Context Protocol) server that empowers AI assistants with KumoRFM intelligence. This server enables:
- 🕸️ Build, manage, and visualize graphs directly from CSV or Parquet files
- 💬 Convert natural language into PQL queries for seamless interaction
- 🤖 Query, analyze, and evaluate predictions from KumoRFM (missing value imputation, temporal forecasting, etc) all without any training required
The KumoRFM MCP server is available for Python 3.10 and above. To install, simply run:
pip install kumo-rfm-mcpAdd to your MCP configuration file (e.g., Claude Desktop's mcp_config.json):
{
"mcpServers": {
"kumo-rfm": {
"command": "python",
"args": ["-m", "kumo_rfm_mcp.server"],
"env": {
"KUMO_API_KEY": "your_api_key_here"
}
}
}
}We provide a single-click installation via our MCP Bundle (MCPB) (e.g., for integration into Claude Desktop):
- Download the
dxtfile from here - Double click to install
The MCP Bundle supports Linux, macOS and Windows, but requires a Python executable to be found in order to create a separate new virtual environment.
See here for the transcript.
claude_desktop_demo.mp4
You can use the KumoRFM MCP directly in your agentic workflows:
|
[Example] |
from crewai import Agent
from crewai_tools import MCPServerAdapter
from mcp import StdioServerParameters
params = StdioServerParameters(
command='python',
args=['-m', 'kumo_rfm_mcp.server'],
env={'KUMO_API_KEY': ...},
)
with MCPServerAdapter(params) as mcp_tools:
agent = Agent(
role=...,
goal=...,
backstory=...,
tools=mcp_tools,
) |
|---|---|
|
[Example] |
from langchain_mcp_adapter.client MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
client = MultiServerMCPClient({
'kumo-rfm': {
'command': 'python',
'args': ['-m', 'kumo_rfm_mcp.server'],
'env': {'KUMO_API_KEY': ...},
}
})
agent = create_react_agent(
llm=...,
tools=await client.get_tools(),
) |
|
[Example] |
from agents import Agent
from agents.mcp import MCPServerStdio
async with MCPServerStdio(params={
'command': 'python',
'args': ['-m', 'kumo_rfm_mcp.server'],
'env': {'KUMO_API_KEY': ...},
}) as server:
agent = Agent(
name=...,
instructions=...,
mcp_servers=[server],
) |
|
|
from claude_code_sdk import query, ClaudeCodeOptions
mcp_servers = {
'kumo-rfm': {
'command': 'python',
'args': ['-m', 'kumo_rfm_mcp.server'],
'env': {'KUMO_API_KEY': ...},
}
}
async for message in query(
prompt=...,
options=ClaudeCodeOptions(
system_prompt=...,
mcp_servers=mcp_servers,
permission_mode='default',
),
):
... |
Browse our examples to get started with agentic workflows powered by KumoRFM.
- 🔍
find_table_files- Searching for tabular files: Find all table-like files (e.g., CSV, Parquet) in a directory. - 🧐
inspect_table_files- Analyzing table structure: Inspect the first rows of table-like files.
- 🗂️
inspect_graph_metadata- Reviewing graph schema: Inspect the current graph metadata. - 🔄
update_graph_metadata- Updating graph schema: Partially update the current graph metadata. - 🖼️
get_mermaid- Creating graph diagram: Return the graph as a Mermaid entity relationship diagram. - 🕸️
materialize_graph- Assembling graph: Materialize the graph based on the current state of the graph metadata to make it available for inference operations. - 📂
lookup_table_rows- Retrieving table entries: Lookup rows in the raw data frame of a table for a list of primary keys.
- 🤖
predict- Running predictive query: Execute a predictive query and return model predictions. - 📊
evaluate- Evaluating predictive query: Evaluate a predictive query and return performance metrics which compares predictions against known ground-truth labels from historical examples. - 🧠
explain- Explaining prediction: Execute a predictive query and explain the model prediction.
KUMO_API_KEY: Authentication is needed once before predicting or evaluating with the KumoRFM model. You can generate your KumoRFM API key for free here. If not set, you can also authenticate on-the-fly in individual session via an OAuth2 flow.
As you work with KumoRFM, if you encounter any problems or things that are confusing or don't work quite right, please open a new issue.
You can also submit general feedback and suggestions here.
Join our Slack!