auto-skill-connector
Enables Claude to search and install skills from a database of ~200k scraped Claude skills, MCP servers, and plugins.
README
auto-skill-connector
An MCP connector that gives Claude Code / Claude Desktop access to a database
of ~200k scraped Claude skills, MCP servers, and plugins. Instead of building
a capability from scratch, Claude can search this database mid-conversation,
read a matching skill's instructions, and follow them immediately — or
install it permanently as a real /skill.
It ships two tools:
recommend_skill(task)— hybrid full-text + semantic search over the skill database. Returns the best match's fullSKILL.mdcontent (or a short list to pick from, if a few skills fit equally well).install_skill(url, name?)— downloads a skill'sSKILL.mdand saves it to~/.claude/skills/<name>/SKILL.md, so Claude Code can invoke it as a normal skill from then on, in any project.
Query embedding happens server-side (Supabase Edge Function), so this
connector only depends on mcp + httpx — no local ML runtime to install.
Install
Claude Code
claude mcp add auto-skill --scope user -- uvx --from git+https://github.com/neelavalareddy/auto-skill-connector auto-skill-mcp
Claude Desktop
Add this to your claude_desktop_config.json (Settings → Developer, or find
it directly — on Windows it's usually under
%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"auto-skill": {
"command": "uvx",
"args": ["--from", "git+https://github.com/neelavalareddy/auto-skill-connector", "auto-skill-mcp"]
}
}
}
Restart Claude Desktop after editing the config.
Both require uv installed (uvx ships with
it) — no cloning or manual pip install needed.
Running it directly
git clone https://github.com/neelavalareddy/auto-skill-connector
cd auto-skill-connector
pip install -e .
python mcp_server.py
How it works
The skill database lives in Supabase (Postgres + pgvector), populated by a
separate scraper that continuously crawls GitHub, npm, and the MCP registry
for Claude skills. This repo only contains the read-only connector — search
queries hit a read-only anon key (RLS grants SELECT only; no writes are
possible with it).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.