Skip to main content
Glama

pack_plugin_dir

Read-only

Pack a real on-disk plugin folder into propose_plugin_preview JSON (modules + schema_json + dependencies).

PREFERRED authoring: write files on disk with the MCP client, then pack once.

Folder layout: Scene.tsx (required entry) schema.json package.json (dependencies) plugin.json (optional id/name/description/category) components/, lib/ (multi-file)

Skips node_modules, dist, lockfiles. Returns propose_plugin_args ready for propose_plugin_preview.

Requires filesystem access (stdio MCP on the machine). On HTTP MCP, use the pack CLI: node mcp-server/scripts/pack-plugin.mjs ./my-plugin --out packed.json

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": {
      "path": "<path>"
    },
    "name": "pack_plugin_dir"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoOverride plugin id (else plugin.json / folder name).
nameNoOverride display name.
pathYesAbsolute or relative path to the plugin project folder.
categoryNo
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, but the description adds real behavior: it skips node_modules, dist and lockfiles, and returns propose_plugin_args ready for propose_plugin_preview. The stated transport requirement (stdio MCP / filesystem access) is context the annotations cannot express. It stops short of describing encoding, error cases, or size limits, so a 4 rather than a 5.

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?

The purpose is front-loaded in one sentence, followed by a compact, scannable layout block and a return-value line. Every item earns its place; the only marginal redundancy is listing both the required entry marker and the multi-file globs, which could be tighter.

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?

With no output schema, the description correctly explains the return value (propose_plugin_args ready for propose_plugin_preview) and covers the environment prerequisite and the folder contract. What remains unstated — failure mode when Scene.tsx is missing, and how the CLI fallback output differs — is minor for this tool's complexity.

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

Parameters4/5

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

Schema coverage is 60%, so some parameters (notably category and description) are only typed, not documented. The description compensates substantially by declaring path a folder with 'Scene.tsx (required entry)' and listing schema.json, package.json and optional plugin.json as the recognized contents, which tells the agent what the path must point at and which override fields it will find there.

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 first sentence names a specific verb and resource ('Pack a real on-disk plugin folder') and states the exact output shape ('propose_plugin_preview JSON (modules + schema_json + dependencies)'). Naming propose_plugin_preview as the downstream consumer cleanly separates it from that sibling.

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?

It gives both a positive rule ('PREFERRED authoring: write files on disk with the MCP client, then pack once') and an explicit exclusion with an alternative ('Requires filesystem access (stdio MCP on the machine). On HTTP MCP, use the pack CLI'). The agent knows when this tool is right and what to do when it is not.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources