npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@mcborov01/skill-manager-mcp

v1.0.0

Published

MCP server + UI to create, edit, and manage AI agent skills

Downloads

18

Readme

Skill Manager MCP

Skill Manager MCP is a combined web UI and MCP server for managing AI agent skills. It gives you a browser-based interface for creating, editing, deleting, searching, and importing skills, and it exposes MCP tools so desktop clients and agent frameworks can discover and load those skills programmatically.

Quick Start

Run the package directly with npx:

npx @mcborov01/skill-manager-mcp

Then open:

http://localhost:3000

The web UI starts on port 3000 by default.

Install Globally

npm install -g @mcborov01/skill-manager-mcp
skill-manager-mcp

This starts the web UI so you can manage your skill library locally.

What You Get

  • A local web UI for managing skills in SQLite
  • Search by keyword or semantic similarity
  • Optional OpenAI embedding support
  • Markdown skill import for bulk loading skills
  • MCP tools for listing and loading skills from compatible clients

MCP Server

The project also ships an MCP server so tools such as Claude Desktop, Cursor, or custom agent runtimes can access the same skill library.

Stdio Transport

Use stdio when your MCP client launches the server as a subprocess.

Direct commands:

node src/mcp.js

You can also wire it into MCP client configuration.

mcp.json or claude_desktop_config.json:

{
  "mcpServers": {
    "skill-manager": {
      "command": "npx",
      "args": ["-y", "--package", "@mcborov01/skill-manager-mcp", "skill-manager-mcp-server"]
    }
  }
}

If the package is installed locally instead:

{
  "mcpServers": {
    "skill-manager": {
      "command": "skill-manager-mcp-server"
    }
  }
}

HTTP Transport

To expose the MCP server over HTTP:

MCP_HTTP_PORT=3001 node src/mcp.js

Then point your MCP client at:

http://localhost:3001/mcp

Embedding Setup

Embedding-based semantic search is optional.

Set OPENAI_API_KEY to enable embeddings. If it is not set, the application falls back to keyword search automatically.

Example:

export OPENAI_API_KEY=your_api_key_here

You can also override the embedding model:

export OPENAI_EMBEDDING_MODEL=text-embedding-3-small

Environment Variables

| Variable | Default | Description | |---|---|---| | PORT | 3000 | Web UI port | | HOST | 127.0.0.1 | Web UI host | | MCP_HTTP_PORT | - | Enable HTTP transport on this port | | OPENAI_API_KEY | - | Enable embedding-based search | | OPENAI_EMBEDDING_MODEL | text-embedding-3-small | Embedding model | | SKILL_DB_PATH | ./skills.db | SQLite database path |

MCP Tools

The MCP server exposes two tools.

list_skills

Searches the skill library and returns matching skills with metadata and relevance scores.

Parameters:

| Parameter | Type | Required | Description | |---|---|---|---| | keywords | string | No | Keywords or natural-language search text | | query | string | No | Alias for natural-language search text | | mode | auto \| keyword \| embedding | No | Search strategy | | limit | number | No | Maximum number of results, from 1 to 100 |

Returns fields including:

  • id
  • title
  • description
  • purpose
  • keywords
  • score
  • matchMode

load_skill

Loads a single skill by its numeric ID.

Parameters:

| Parameter | Type | Required | Description | |---|---|---|---| | id | number | Yes | Skill ID from list_skills |

Returns the full skill record, including the stored markdown content and metadata.

Markdown Import

The web UI includes a markdown import form so you can bulk-create skills from pasted text.

Supported formats include:

  • Frontmatter-based skill documents
  • [Skill: Title] blocks
  • Markdown documents with # Heading titles

Example frontmatter format:

---
name: PostgreSQL Expert
description: Guidance for PostgreSQL schema design and operations
purpose: Help agents work with production PostgreSQL safely
keywords: postgres, sql, database, indexing
---
# PostgreSQL Expert

Use this skill when working with PostgreSQL migrations, indexing strategy, query review, and incident response.

You can paste one or multiple skills into the import form. When embeddings are enabled, imported skills also receive generated embeddings for semantic search.

Local Development

If you are working from the repository directly:

npm install
node src/web.js

For stdio MCP:

node src/mcp.js

For the web UI, open:

http://localhost:3000

Storage

Skills are stored in a local SQLite database. By default the database file is:

./skills.db

Override it with SKILL_DB_PATH if you want to store data elsewhere.