Msty Admin MCP

Import tool config

import_tool_config

Save a Toolbox tool config as a JSON pack without writing to the Studio database. Flags configs with command, args or env as launch-risk and keeps them pack-only.

Instructions

Save a Toolbox tool config as a JSON pack. Never writes the Studio database. Use this for tools. Use import_studio_pack for personas, prompts, skills and toolsets. Configs with command, args or env are flagged as running a program on your machine and stay pack-only. Returns JSON with pack_path, wrote=false, and launch_risk when present.

Input Schema

Name	Required	Description	Default
`confirm`	No	Accepted for symmetry. Tools are never inserted into SQLite. Default false.
`tool_data`	Yes	Tool object with name, toolId and config. command, args and env are allowed in the pack but never inserted into SQLite.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv6.2.1Nov 1, 2026

addedInput schema / properties / confirm / description

Added value: +"Accepted for symmetry. Tools are never inserted into SQLite. Default false."

addedInput schema / properties / tool_data / description

Added value: +"Tool object with name, toolId and config. command, args and env are allowed in the pack but never inserted into SQLite."

Changed1 schema field changedv6.1.5Oct 16, 2026

addedInput schema / properties / confirm

Added value: +{
+  "default": false,
+  "title": "Confirm",
+  "type": "boolean"
+}

First observedv5.0.0May 26, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only mark this as a non-readonly, non-destructive, non-idempotent write; the description goes well beyond them by disclosing that the Studio SQLite database is never touched, that configs with command/args/env are flagged as machine-executing and confined to the pack, and what the response contains (pack_path, wrote=false, launch_risk). That launch-risk disclosure is safety-relevant context the annotations cannot express.

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?

Five short sentences, front-loaded with the core action and the 'never writes' constraint, then routing, then the exception case, then the return shape. No sentence is redundant and the highest-risk information is not buried.

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?

Despite a nested tool_data object and a mutation-adjacent operation, the definition covers what is persisted, what is never persisted, the flagging rule, the sibling alternative, and the return payload. With an output schema present, nothing an agent needs in order to call this correctly is missing.

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% and the confirm parameter already documents its symmetry-only role, so the schema carries the parameter burden. The description restates the command/args/env behavior from the schema rather than adding new field-level meaning, so baseline 3 is appropriate.

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 ('Save a Toolbox tool config as a JSON pack') plus a hard scope constraint ('Never writes the Studio database'). It explicitly separates itself from import_studio_pack by domain (tools vs personas/prompts/skills/toolsets), so an agent can route without opening the schema.

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 explicit when-to-use ('Use this for tools') and names the alternative with the condition that selects it ('Use import_studio_pack for personas, prompts, skills and toolsets'). The pack-only exclusion for configs containing command/args/env is stated as a behavioral rule rather than left to inference.

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

Deploy Server