skillsmp-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port when using http transport (default: 3000) | 3000 |
| TRANSPORT | No | Transport type: stdio (default) or http | stdio |
| SKILLSMP_API_KEY | Yes | Your SkillsMP API key |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| skillsmp_searchA | Search SkillsMP marketplace for AI coding skills by keywords. Parameters:
Returns skills with name, description, author, stars, and GitHub URL. |
| skillsmp_ai_searchA | Semantic search for skills using natural language queries. Powered by AI to understand intent. Use this when keywords aren't enough - describe what you want to accomplish. Parameters:
Examples: "tools for web scraping", "help with React testing", "automate deployments" |
| skillsmp_get_skill_contentA | Read skill file content (SKILL.md) from a GitHub repository. Use to preview a skill before installing. Parameters:
If path has no skill.md, returns directory listing. |
| skillsmp_list_repo_skillsA | List all available skills in a GitHub repository without installing. Parameters:
Returns skill names and descriptions found in the repository. |
| skillsmp_install_skillA | Install skills from GitHub to AI coding agents. Parameters:
Example: source="anthropics/claude-code", skills="frontend-design", agents="claude-code" |
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 5 tools
Each tool has a clearly distinct purpose: semantic search, content reading, installation, repo listing, and keyword search. No overlap.
All tools use the 'skillsmp_' prefix followed by a verb_noun pattern (ai_search, get_skill_content, install_skill, list_repo_skills, search), creating a predictable and clear naming convention.
Five tools is an ideal size for a skills marketplace MCP server, covering the core workflow of discovery, preview, and installation without being excessive.
The tool set covers the essential lifecycle (search, preview, install) for skills. Missing uninstall or update tools, but these are secondary to the primary use case.