pkgguard
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| authorize_install_commandB | Authorize an agent-generated install command before it reaches a package manager. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of misselection or overlap. The single tool's purpose—authorizing a generated install command—is clearly distinct and unambiguous.
The lone name 'authorize_install_command' uses a clean snake_case verb_noun pattern. There are no other tools to conflict with or deviate from this convention.
A single tool is borderline thin even for a narrow gate-focused server. A minimal surface like this can work as a focused approval hook, but it leaves little room for related operations.
The core authorize action is covered, but there is no way to inspect policy, retrieve prior decisions, or explain a denial. Agents hitting a blocked command have no follow-up path, which is a notable but workable gap for such a narrow domain.