Skip to main content
Glama
Sign In
SAS MCP Server

SAS MCP Server

Official
by sassoftware
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Create Model Project

create_model_project
Idempotent

Creates a SAS Model Manager project in a model repository to organize models, returning an existing project when the name already exists.

Instructions

Create a SAS Model Manager project to hold models.

Projects live in a model repository, not in SAS Content. A project of that name already in the repository is returned instead of a second one (status exists). register_model also creates the project it names when it does not exist, so this is needed only to prepare one.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "create_model_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe project's name.
folderNoA folder inside the repository to put the project in, created when missing. One folder name, not a path.
functionNo``classification`` (default), ``prediction`` or another Model Manager function.classification
repositoryNoRepository name or ID (default: the deployment's ``MCP_DEFAULT_MODEL_REPOSITORY``, ``Public`` unless changed; see ``list_model_repositories``).
descriptionNoOptional description.
target_eventNoThe event value, for a binary or nominal target.
target_levelNo``binary``, ``nominal`` or ``interval``.
target_variableNoThe target the project's models predict.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.19.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description goes further by explaining the mechanism: an existing project of the same name is returned rather than duplicated, surfacing a ``status`` of ``exists``. That is concrete behavioral detail an agent cannot derive from the hints alone.

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

Conciseness4/5

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

Two tight paragraphs, front-loaded with the purpose and then the caveat about register_model. Minor deduction for the double-backtick markup around ``status`` and ``exists``, which adds visual noise without meaning.

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

Completeness5/5

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

For an idempotent create with an output schema, the description covers what matters: what it creates, where it lives, and what happens on a name collision. Return-value details are rightly left to the output schema.

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%, with all eight parameters including defaults and the repository fallback documented in the schema. The description adds no parameter-specific meaning such as target_variable/target_level interplay or folder nesting rules, so it earns the baseline rather than more.

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?

States a specific verb and resource: 'Create a SAS Model Manager project to hold models.' It also disambiguates the domain by noting projects live in a model repository, not SAS Content, which separates it from content-creation siblings like create_folder.

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?

Gives an explicit when-not: register_model already creates the project it names, so this tool is 'needed only to prepare one.' That single clause tells an agent precisely when this tool is the right choice versus a named sibling.

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

Deploy Server

Other Tools