extract-mcp-servers-from-urlLABSCO SUMMARY
It reads the page with a model, so the extraction is not a scraper you maintain.
Point it at a listing page or paste the content in, and it returns the servers it found; submission then posts one to a directory. The extraction runs through an OpenAI-compatible endpoint you configure, so the model and base URL are your choice.
What it is
A collector for MCP servers found on the web. It extracts server entries from a URL or from raw content you paste in, and submits one to a directory.
What you get
- extract-mcp-servers-from-url — MCP servers extracted from a page you name
- extract-mcp-servers-from-content — the same, from content passed in directly
- submit-mcp-server — one server submitted to a directory such as mcp.so, with an optional avatar URL
Requirements
An OpenAI-compatible API key, base URL and model name in the environment, plus the submit endpoint of the directory you are posting to. It runs with uv or uvx.
Setup effort
One command plus a key — uvx mcp-server-collector, then supply credentials
USE CASES
01
Harvesting servers from a curated list
Give it the URL and take back structured entries, instead of copying rows by hand.
02
Turning a README somebody sent you into entries
Paste the content in directly when the source is not a page you can link to.
03
Getting your own server listed
Submit it to the directory with its avatar, from the same session that found it.
3 tools
Listed in project docs. Your client may show a different list.
extract-mcp-servers-from-contentsubmit-mcp-serverBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- uvx on PATH
- OPENAI_API_KEY, OPENAI_BASE_URL and OPENAI_MODEL for an OpenAI-compatible model
- MCP_SERVER_SUBMIT_URL, the submit endpoint of the directory you post to (mcp.so uses https://mcp.so/api/submit-project)
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mcp-server-collectorMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"mcp-server-collector": {
"command": "uvx",
"args": [
"mcp-server-collector"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"OPENAI_BASE_URL": "https://api.openai.com/v1",
"OPENAI_MODEL": "gpt-4o-mini",
"MCP_SERVER_SUBMIT_URL": "https://mcp.so/api/submit-project"
}
}
}
}
