Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SKILLS_DIRNoPath to the directory containing Agent Skills

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

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": true
}
resources
{
  "subscribe": true,
  "listChanged": true
}
extensions
{
  "io.modelcontextprotocol/skills": {}
}
completions
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
load-skillA

Load a skill's full instructions. Returns the complete SKILL.md content with step-by-step guidance, examples, and file references to follow.

IMPORTANT: When a skill is relevant to the user's task, you must invoke this tool IMMEDIATELY as your first action. NEVER just announce or mention a skill without actually calling this tool. This is a BLOCKING REQUIREMENT: invoke this tool BEFORE generating any other response about the task.

skill-resourceA

Read files referenced by skill instructions (scripts, snippets, templates). Use when skill instructions mention specific files to read or copy. Pass a directory path (e.g., 'templates') to read all files in that directory at once. Text files are returned as text; a binary file is returned as an embedded base64 resource.

skill-configA

Open the skills directory configuration UI. Use when user wants to configure, add, or remove skill directories.

skill-config-add-directoryC

Add a skills directory to the configuration.

skill-config-remove-directoryC

Remove a skills directory from the configuration.

skill-config-add-allowed-orgB

Add a GitHub organization to the allowed list for skill repos.

skill-config-remove-allowed-orgC

Remove a GitHub organization from the allowed list.

skill-config-add-allowed-originB

Add an HTTPS origin (e.g. https://example.com) to the allowed list for well-known publishers.

skill-config-remove-allowed-originB

Remove an HTTPS origin from the well-known allowed list.

skill-config-set-static-modeB

Enable or disable static mode (freezes skills list at startup).

skill-displayC

Open the skill display UI to view available skills and configure their invocation settings. Use when user wants to see skills or toggle assistant/user invocation.

skill-display-update-invocationC

Update invocation settings for a skill.

skill-display-reset-overrideA

Reset a skill's invocation settings to frontmatter defaults.

Prompts

Interactive templates invoked by user choice

NameDescription
skillLoad a skill by name with auto-completion. # Skills When a user's task matches a skill description below: 1) activate it, 2) follow its instructions completely. <available_skills> <skill> <name>skilljack-docs</name> <description>Complete documentation for the Skilljack MCP server - tools, prompts, resources, configuration, and architecture reference.</description> <uri>skill://skilljack-docs/SKILL.md</uri> <location>/app/skills/skilljack-docs/SKILL.md</location> </skill> </available_skills>
skilljack-docsComplete documentation for the Skilljack MCP server - tools, prompts, resources, configuration, and architecture reference.
skillsOpen the skills list UI to view all available skills and manage their invocation settings.
skill-configOpen the skills configuration UI to manage skill directories and GitHub sources.

Resources

Contextual data attached and managed by the client

NameDescription
Skill IndexSEP-2640 Agent Skills discovery index
ui://skill-config/mcp-app.html
ui://skill-display/skill-display.html
skilljack-docsComplete documentation for the Skilljack MCP server - tools, prompts, resources, configuration, and architecture reference.

TDQS

B3.2/5.0

Scored across 13 tools

Disambiguation4/5

The core tools (load-skill, skill-resource) are clearly distinct, and the add/remove config pairs (directory, org, origin) target unambiguous resources. The only mild confusion is between the UI-opener tools (skill-config, skill-display) and the granular operations they overlap with, but descriptions help distinguish them.

Naming Consistency4/5

Nearly all tools follow a predictable kebab-case skill-{subsystem}-{action}-{target} pattern (skill-config-add-directory, skill-display-reset-override). The outliers load-skill and skill-resource use a different verb/noun-only structure, but the set remains readable and mostly consistent.

Tool Count4/5

13 tools sits comfortably in the well-scoped 3-15 range for a skill-management server. The surface leans heavily toward configuration (8 of 13), which is slightly unbalanced but each tool still earns its place.

Completeness4/5

Config resources (directories, orgs, origins, static mode) all have add/remove or set coverage, and display settings have update/reset. The main gap is the absence of a programmatic list-skills tool, since enumeration is only exposed through the skill-display UI, but core load/resource workflows are covered.

Maintenance

ActivityMaintained
ResponsivenessResponsive