mcp-server-collector MCP server
About
A MCP Server used to collect MCP Servers over the internet.
Explore
- Extracts MCP server details from a given URL.
- Extracts MCP server details from provided content text.
- Submits an MCP server to a directory like mcp.so.
- Requires only an OpenAI API key for extraction.
- Supports custom OpenAI base URL and model selection.
- Easily configurable for Claude Desktop.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
mcp-server-collector MCP serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
.env file is required to be set up.
OPENAI_API_KEY="sk-xxx"
OPENAI_BASE_URL="https://api.openai.com/v1"
OPENAI_MODEL="gpt-4o-mini"
MCP_SERVER_SUBMIT_URL="https://mcp.so/api/submit-project"
The server implements 3 tools:
- extract-mcp-servers-from-url: Extracts MCP Servers from given URL.
- Takes "url" as required string argument
- extract-mcp-servers-from-content: Extracts MCP Servers from given content.
- Takes "content" as required string argument
- submit-mcp-server: Submits a MCP Server to the MCP Server Directory like mcp.so.
- Takes "url" as required string argument and "avatar_url" as optional string argument
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-server-collector mcp server": {
"mcp-server-collector": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"mcp-server-collector": {
"command": "uv",
"args": [
"sync"
]
}
}A MCP Server used to collect MCP Servers over the internet.
Components
Resources
No resources yet.
Prompts
No prompts yet.
Tools
The server implements 3 tools:
- extract-mcp-servers-from-url: Extracts MCP Servers from given URL.
- Takes "url" as required string argument
- extract-mcp-servers-from-content: Extracts MCP Servers from given content.
- Takes "content" as required string argument
- submit-mcp-server: Submits a MCP Server to the MCP Server Directory like mcp.so.
- Takes "url" as required string argument and "avatar_url" as optional string argument
Configuration
.env file is required to be set up.
OPENAI_API_KEY="sk-xxx"
OPENAI_BASE_URL="https://api.openai.com/v1"
OPENAI_MODEL="gpt-4o-mini"
MCP_SERVER_SUBMIT_URL="https://mcp.so/api/submit-project"
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
<details>
<summary>Development/Unpublished Servers Configuration</summary>
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
},
"mcp-server-collector": {
"command": "uv",
"args": [
"--directory",
"path-to/mcp-server-collector",
"run",
"mcp-server-collector"
],
"env": {
"OPENAI_API_KEY": "sk-xxx",
"OPENAI_BASE_URL": "https://api.openai.com/v1",
"OPENAI_MODEL": "gpt-4o-mini",
"MCP_SERVER_SUBMIT_URL": "https://mcp.so/api/submit-project"
}
}
}
</details>
<details>
<summary>Published Servers Configuration</summary>
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
},
"mcp-server-collector": {
"command": "uvx",
"args": [
"mcp-server-collector"
],
"env": {
"OPENAI_API_KEY": "sk-xxx",
"OPENAI_BASE_URL": "https://api.openai.com/v1",
"OPENAI_MODEL": "gpt-4o-mini",
"MCP_SERVER_SUBMIT_URL": "https://mcp.so/api/submit-project"
}
}
}
</details>
Development
Building and Publishing
To prepare the package for distribution:
1. Sync dependencies and update lockfile:
uv sync
2. Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
3. Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token: --token or UV_PUBLISH_TOKEN
- Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging
experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory path-to/mcp-server-collector run mcp-server-collector
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Community
- MCP Server Telegram
- MCP Server Discord
About the author
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
