skillsmcp
Click on "Deploy 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., "@skillsmcp list available skills"
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.
skillsmcp
MCP server that exposes Agent Skills to AI agents via the Model Context Protocol.
Agent Skills are reusable, portable instruction sets that guide AI coding agents. This server makes them discoverable and activatable as MCP tools, following the progressive disclosure pattern from the Agent Skills specification.
Prerequisites
uv — fast Python package manager
Install with Homebrew:
brew install uvRelated MCP server: DPS-Superskills-MCP
Install
uv tool install git+https://github.com/aviddiviner/skillsmcp.gitThis installs skillsmcp as a command on your PATH. To update later:
uv tool upgrade skillsmcpConfigure
Zed
Add to your settings (~/.config/zed/settings.json):
{
"context_servers": {
"skillsmcp": {
"command": "uvx",
"args": ["skillsmcp"]
}
}
}Claude Desktop
Add to your Claude config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"skillsmcp": {
"command": "uvx",
"args": ["skillsmcp"]
}
}
}Other MCP Clients
Any client that supports MCP's stdio transport can use this server. Run it directly:
uvx skillsmcpTools
The server exposes three MCP tools:
Tool | Description |
| Discover all available skills with names and descriptions |
| Load a skill's full instructions by name |
| Read supporting files from a skill's directory |
All tools accept an optional project_roots parameter — a list of project directories to scan for project-level skills. User-level skills (~/.agents/skills/, ~/.claude/skills/) are always included. When project_roots is not provided, the server falls back to its working directory.
Adding Skills
Skills are directories containing a SKILL.md file with YAML frontmatter:
~/.agents/skills/
└── my-skill/
├── SKILL.md
├── scripts/
│ └── helper.py
└── references/
└── REFERENCE.mdExample SKILL.md:
---
name: my-skill
description: A short description of what this skill does and when to use it.
---
# My Skill
Instructions for the AI agent go here...Skill Directories
The server scans the following directories in precedence order (first-found wins for name collisions):
Project-level (highest priority):
<project>/.agents/skills/<project>/.claude/skills/
User-level:
~/.agents/skills/~/.claude/skills/
Project-level skills override user-level skills with the same name.
Development
git clone https://github.com/aviddiviner/skillsmcp.git
cd skillsmcp
# Install in development mode
uv sync
# Run the server directly
uv run skillsmcpLearn More
Agent Skills specification — the full format spec
Example skills — official skill examples
skills.sh — browse and install community skills
FastMCP — the Python MCP framework powering this server
License
MIT
Available Tools
3 toolsactivate_skillA
Activate a skill by name, loading its full instructions and listing supporting files.
Inputs: name (required), project_roots. Returns: result
list_skillsA
List all available agent skills with their names and descriptions.
Scans project-level and user-level skill directories for SKILL.md files. Returns a JSON array of objects with name, description, and path for each skill.
Inputs: project_roots. Returns: result
read_skill_fileB
Read a supporting file from a skill's directory.
Inputs: file_path (required), skill_name (required), project_roots. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: listing skills, activating a skill, and reading a skill's supporting files. No overlap or ambiguity exists between them.
All tool names follow a consistent verb_noun snake_case pattern: list_skills, activate_skill, read_skill_file. The naming is predictable and uniform.
With 3 tools, the server is well-scoped for its purpose of managing and accessing skills. Each tool serves a necessary function without redundancy.
The tool surface covers the full life cycle of interacting with skills: discovery (list), retrieval of details (activate), and access to supporting files. No obvious missing operations for the stated domain.
Maintenance
Related MCP Connectors
Governed AI agent skills — one library, distributed to devs and exposed to remote agents over MCP.
Search & install 13,000+ AI agent skills from skills-hub.ai inside any MCP tool.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Search and inspect source-pinned agent skills, plugins and tools through a free public MCP.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceLoads Agent Skills from markdown files, exposing them as MCP tools or system prompts for AI agents.92 PyPI31MIT
- AlicenseAqualityDmaintenanceExposes 31 high-assurance agentic coding skills as MCP tools and resources, enabling AI agents to invoke structured workflows across DISCIPLINE, TECHNIQUE, KNOWLEDGE LAYER, and REFERENCE registers.5Apache 2.0
- AlicenseNot gradedqualityCmaintenanceExposes an agent's skills as MCP tools, allowing any MCP client to route requests and load skills on demand from a single .3md file.20 npm1MIT
- AlicenseNot gradedqualityCmaintenanceExposes MCP tools to list, search, and load Markdown skills from a local folder, enabling coding agents to discover and reuse procedural knowledge.MIT