Iflow Mcp Kumo Ai Kumo Rfm

📖 Introduction

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

🚀 Installation

🐍 Traditional MCP Server

The KumoRFM MCP server is available for Python 3.10 and above. To install, simply run:

pip install kumo-rfm-mcp

Add 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"
      }
    }
  }
}

HTTP Transport

For HTTP-native MCP clients such as a Snowflake Native App, run the server with streamable-http instead of stdio:

KUMO_API_KEY=<YOUR-KUMO-API-KEY> \
MCP_BEARER_TOKEN=<SHARED-MCP-TOKEN> \
python -m kumo_rfm_mcp.server \
  --transport streamable-http \
  --host 0.0.0.0 \
  --port 8000 \
  --path /mcp

Notes:

• Set KUMO_API_KEY up front for headless deployments. This avoids the browser-based OAuth flow.
• If your MCP client cannot inject environment variables, call the authenticate tool with an api_key argument once at session start.
• If MCP_BEARER_TOKEN is set, the HTTP endpoint requires Authorization: Bearer <SHARED-MCP-TOKEN>.

⚡ MCP Bundle

We provide a single-click installation via our MCP Bundle (MCPB) (e.g., for integration into Claude Desktop):

1. Download the dxt file from here
2. 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.

Claude code

To include the server in claude code use:

claude mcp add --transport stdio kumo-rfm-mcp --env KUMO_API_KEY=<YOUR-API-KEY> -- python -m kumo_rfm_mcp.server --port 8000

🎬 Claude Desktop Demo

See here for the transcript.

https://github.com/user-attachments/assets/56192b0b-d9df-425f-9c10-8517c754420f

🔬 Agentic Workflows

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.

📚 Available Tools

I/O Operations

• 🔍 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.

Graph Management

• 🗂️ 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.

Model Execution

• 🤖 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.

🔧 Configuration

Environment Variables

• 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.

We love your feedback! :heart:

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 :octocat:issue. You can also submit general feedback and suggestions here. Join our Slack!