Skip to main content
Glama
Sign In
M-Pineapple

Msty Admin MCP

by M-Pineapple
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Set model settings

set_model_settings
Destructive

Create a tuned Ollama model variant from an installed base model; preview the Modelfile and settings, then set confirm=true to write without overwriting existing names.

Instructions

Create a tuned Ollama variant via /api/create from an installed base model. Use install_model first if the base is missing. Does not overwrite an existing name. Needs confirm=true to write. Returns JSON with wrote, variant and a Modelfile preview.

Input Schema

NameRequiredDescriptionDefault
top_pNoNucleus sampling 0 to 1. Omit to leave unset.
systemNoSystem prompt for the variant. Max 20000 characters. Omit to leave unset.
confirmNoSet true to POST /api/create. Default false (preview).
num_ctxNoContext window in tokens. Positive integer. Omit to leave unset.
base_modelYesInstalled base model name, for example llama3.2:3b.
temperatureNoSampling temperature 0 to 2. Omit to leave unset.
variant_nameYesNew variant name to create. Must not already exist.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv6.2.1
    • addedInput schema / properties / base_model / description
      Added value: +"Installed base model name, for example llama3.2:3b."
    • addedInput schema / properties / confirm / description
      Added value: +"Set true to POST /api/create. Default false (preview)."
    • addedInput schema / properties / num_ctx / description
      Added value: +"Context window in tokens. Positive integer. Omit to leave unset."
    • addedInput schema / properties / system / description
      Added value: +"System prompt for the variant. Max 20000 characters. Omit to leave unset."
    • addedInput schema / properties / temperature / description
      Added value: +"Sampling temperature 0 to 2. Omit to leave unset."
    • addedInput schema / properties / top_p / description
      Added value: +"Nucleus sampling 0 to 1. Omit to leave unset."
    • addedInput schema / properties / variant_name / description
      Added value: +"New variant name to create. Must not already exist."
  2. Addedv6.2.0

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations, it discloses the underlying /api/create call, the non-overwrite behavior for existing names, the confirm gate, and the return fields. It does not fully reconcile the destructiveHint=true annotation with the additive 'does not overwrite' behavior, but no direct contradiction is present.

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

Conciseness5/5

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

The description is four tight sentences with the core creation action front-loaded. Every sentence carries operational value: prerequisite, non-overwrite rule, confirm requirement, and return shape.

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?

Given the annotations and the output schema, the description covers the key operational facts an agent needs: base model prerequisite, write gating via confirm, existing-name protection, and response contents. Nothing critical is missing for correct invocation.

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 coverage is 100%, so all seven parameters are already documented in the schema. The description reinforces confirm and variant-name semantics but adds little meaning for the tuning parameters such as temperature, top_p, system, and num_ctx.

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 states a specific verb and resource: create a tuned Ollama variant via /api/create from an installed base model. It also distinguishes itself from install_model by telling the agent to use install_model first when the base is missing.

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

Usage Guidelines4/5

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

It gives clear prerequisite context: the base model must already be installed, and confirm=true is required to actually write. It does not fully enumerate when not to use the tool or all alternatives, but the install_model handoff is explicit.

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