The MCP Skills Server is a production-ready server that dynamically loads and exposes skills from a mounted volume with hot-reloading support, compliant with the Model Context Protocol (MCP).
From the registry: MCP server that loads and serves skills from a mounted directory with hot reload.
$ mkdir -p ~/claude-skillsPlease install the `mcp-skill-hub` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Docker** — Docker installed for recommended container deployment
- **Skills directory** — Directory containing skill folders, each with a SKILL.md Run: `mkdir -p ~/claude-skills`
Canonical MCP server config (stdio transport):
- command: `docker`
- args: ["run","-i","--rm","-v","${HOME}/claude-skills:/skills:ro","mcp-skill-hub"]
- optional environment variables:
- `MCP_SKILLS_DIR`: Root skills directory inside container (example: `/skills`)
- `MCP_SKILLS_HOT_RELOAD`: Enable hot-reloading (example: `true`)
- `MCP_SKILLS_LOG_LEVEL`: Log level (example: `INFO`)
Note: Also runnable via Poetry locally. Docker image must be built first.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP_SKILLS_DIRrequiredRoot directory containing skill folders.MCP_SKILLS_LOG_LEVELLog level (DEBUG, INFO, WARNING, ERROR).AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.