Marginalia Search
STDIOMCP server providing access to Marginalia Search for finding non-commercial web content.
MCP server providing access to Marginalia Search for finding non-commercial web content.
An MCP (Model Context Protocol) server that provides access to Marginalia Search, a search engine focused on finding non-commercial content and hidden gems of the internet.
npm install npm run build
The server can be configured using environment variables:
MARGINALIA_API_KEY
: Your Marginalia Search API key (optional, defaults to public access)To request a dedicated API key, contact: [email protected]
The server provides the following MCP tool:
Search the web using Marginalia Search with the following parameters:
query
(required): Search query stringindex
(optional): Search index number (corresponds to dropdown in main GUI)count
(optional): Number of results to return (1-100, default: 10)Example usage through MCP:
const result = await mcp.useTool("marginalia", "search", { query: "interesting non-commercial websites", count: 5 });
The search results are returned in the following format:
{ "query": "your search query", "license": "license information", "results": [ { "url": "result url", "title": "page title", "description": "page description" } // ... more results ] }
The server includes robust error handling for:
To enable text-to-speech capabilities using the say MCP server, add the following configuration:
Add to ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
:
{ "mcpServers": { "say": { "command": "node", "args": ["/Users/barton/worlds/servers/src/say-mcp-server/build/index.js"] } } }
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
:
{ "mcpServers": { "say": { "command": "node", "args": ["/Users/barton/worlds/servers/src/say-mcp-server/build/index.js"] } } }
The say MCP server provides text-to-speech capabilities with multiple voices and languages. Available tools:
speak
: Read text aloud using specified voice and ratelist_voices
: List all available text-to-speech voicesMIT License - See LICENSE file for details