Skip to main content
Glama
kumo-ai

KumoRFM MCP Server

Official
by kumo-ai

🧠 Explaining prediction…

explain
Read-onlyIdempotent

Execute a predictive query for a single entity and receive a model explanation for the prediction.

Instructions

Execute a predictive query and explain the model prediction.

The graph needs to be materialized and the session needs to be authenticated before the KumoRFM model can start generating an explanation for a prediction.

Only a single entity prediction can be explained at a time. The run_mode will be fixed to 'fast' mode for explainability. Note that the model prediction returned by the explanation might differ slightly from the result of the predict tool due to floating-point precision. Ignore such small differences.

Important: Before executing or suggesting any predictive queries, read the documentation first at 'kumo://docs/predictive-query'.

Important: Before analyzing the explanation output, read the documentation first at 'kumo://docs/explainability'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe predictive query string, e.g., 'PREDICT COUNT(orders.*, 0, 30, days)>0 FOR EACH users.user_id' or 'PREDICT users.age FOR EACH users.user_id'
indexYesThe primary key (entity index) of the prediction to explain
anchor_timeNoThe anchor time for which we are making a prediction for the the future. If `None`, will use the maximum timestamp in the data as anchor time. If 'entity', will use the timestamp of the entity's time column as anchor time (only valid for static predictive queries for which the entity table contains a time column), which is useful to prevent future data leakage when imputing missing values on facts, e.g., predicting whether a transaction is fraudulent should happen at the point in time the transaction was created.
num_neighborsNoThe number of neighbors to sample for each hop to create subgraphs. For example, `[24, 12]` samples 24 neighbors in the first hop and 12 neighbors in the second hop. If `None` (recommended), will use two-hop sampling with 32 neighbors in 'fast' mode, and 64 neighbors otherwise in each hop. Up to 6-hop subgraphs are supported. Decreasing the number of neighbors per hop can prevent oversmoothing. Increasing the number of neighbors per hop allows the model to look at a larger historical time window. Increasing the number of hops can improve performance in case important signal is far away from the entity table, but can result in massive subgraphs. We advise to let the number of neighbors gradually shrink down in later hops to prevent recursive neighbor explosion, e.g., `num_neighbors=[32, 32, 4, 4, 2, 2]`, if more hops are required.
max_pq_iterationsNoThe maximum number of iterations to perform to collect valid training/in-context examples. It is advised to increase the number of iterations in case the model fails to find the upper bound of supported training examples w.r.t. the run mode, *i.e.* 1000 for 'fast', 5000 for 'normal' and 10000 for 'best'.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
predictionYes
explanationYes
logsNoPrediction-specific log messages such as number of context examples, the underlying task type and the label distribution
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds value by disclosing that the returned prediction may differ from `predict` due to floating-point precision, and that the run mode is fixed. This provides context beyond what annotations offer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately sized but includes repetitive directives (two 'Important:' notes) that could be merged. It is front-loaded with the main purpose, but could be streamlined for better conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity and the presence of an output schema, the description effectively covers prerequisites, limitations (single entity, fixed run_mode, precision differences), and provides documentation links. It fairly well equips the AI agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds minimal extra parameter information (e.g., fixed run_mode) but mostly reiterates constraints already documented in the schema. No significant additional semantic value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool's action: 'Execute a predictive query and explain the model prediction.' It clearly distinguishes from the sibling `predict` tool by noting that the explanation may differ due to floating-point precision and that only a single entity can be explained at a time.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit preconditions: graph must be materialized and session authenticated. It specifies that only a single entity is supported and that `run_mode` is fixed to 'fast'. It also directs users to documentation before executing or analyzing, offering clear guidance on when and how to use the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kumo-ai/kumo-rfm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server