AI Skills MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AI Skills MCP Serverpack context for installing python dependencies"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI Skills MCP Server
MCP server that compiles ai-skills skill definitions and serves them to AI agents over the Model Context Protocol. Skills are bundled — zero config required.
npx ai-skills-mcp startRegister in your MCP client config:
{
"mcpServers": {
"ai-skills": {
"command": "npx",
"args": ["ai-skills-mcp", "start"]
}
}
}How the AI Uses Skills
Skills are not automatically injected into the AI's context. The MCP server exposes tools that the AI chooses to call. The typical flow:
AI receives a task (e.g. "install python dependencies")
AI calls
pack_context("install python dependencies")— the server finds relevant skills (uv, anti-global-install, etc.), resolves their transitive dependencies, and returns packed skill content within token limitsAI reads the returned skill instructions and follows them
This requires the AI to know about pack_context. See docs/ai-workflow.md for setup guidance and the skill-loader skill which teaches this pattern.
Related MCP server: SkillMCP
Commands
Command | Description |
| Start MCP server (stdio or SSE) |
| Compile skills and save registry |
| List all compiled skills |
start flags
Flag | Default | Description |
| (bundled) | Override path to skills directory |
|
|
|
|
| Port for SSE transport |
|
| JSON registry path |
| — | Use SQLite registry instead of JSON |
| — | Skip registry persistence |
MCP Tools
Tool | Description |
| List all compiled skills |
| Get full compiled skill by name |
| Search skills by keyword |
| Get dependency graph for a skill |
| Build a context pack for a task |
| Find skills that reference a given skill |
| Registry statistics |
MCP Resources
URI | Description |
| Full compiled skill |
| Dependencies of a skill |
| Skills that reference this one |
Documentation
Doc | Description |
How the AI discovers and uses skills | |
Compiler, resolver, packer internals | |
Project design and data flow | |
Full MCP tool and resource reference | |
How to write a SKILL.md | |
Scope, limitations, roadmap |
Architecture
flowchart LR
Skills["skills/"] --> Compiler["SkillCompiler"]
Compiler --> Resolver["DependencyResolver"]
Compiler --> Packer["ContextPacker"]
Compiler --> Registry["Registry"]
Resolver --> MCP["MCP Server"]
Packer --> MCP
Registry --> MCP
MCP --> Tools["7 tools"]
MCP --> Resources["3 resource URIs"]
style Skills fill:#1a1a2e,color:#eee
style Compiler fill:#4a90d9,color:#fff
style Resolver fill:#50b86c,color:#fff
style Packer fill:#e6a020,color:#fff
style Registry fill:#9b59b6,color:#fff
style MCP fill:#1abc9c,color:#fff
style Tools fill:#34495e,color:#eee
style Resources fill:#34495e,color:#eeeSee docs/architecture.md for the full import graph and docs/how-it-works.md for the pipeline.
Transports
stdio (default) — Claude Desktop, Cursor, etc.
SSE — remote deployments:
--transport sse --port 3000
Registries
JSON (default) — file-based, easy to debug
SQLite — persistent, queryable:
--sqlite ./registry.dbMemory — ephemeral,
--no-registry
Development
npm install
npm run build
npm start -- --no-registry
npm testThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/coff33ninja/ai-skills-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server