mcpField
M
Marginalia MCP Server

Marginalia MCP Server

Local
github.com/bmorphismSearch9Updated 94w ago

About Marginalia MCP Server

Marginalia MCP Server lets MCP clients search Marginalia Search, which focuses on non-commercial websites and lesser-known corners of the web. It supports configurable indexes and result counts.

Key features

  1. 01Search Marginalia Search
  2. 02Select search index
  3. 03Set result count
  4. 04Handle rate limits and errors

Use cases

  1. 01Find non-commercial websites
  2. 02Search lesser-known web pages

MCP support

It exposes a `search` tool to MCP clients, with query, optional index, and result count parameters.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Marginalia MCP Server

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.

Features

  • Search the web using Marginalia Search API
  • Configurable search parameters including index and result count
  • Rate limiting protection with helpful error messages
  • Built using the MCP SDK for seamless integration

Installation

npm install
npm run build

Configuration

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]

Usage

The server provides the following MCP tool:

search

Search the web using Marginalia Search with the following parameters:

  • query (required): Search query string
  • index (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
});

Response Format

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
  ]
}

Error Handling

The server includes robust error handling for:

  • Rate limiting (503 responses)
  • Invalid requests
  • Network errors
  • API-specific errors

Adding Text-to-Speech Support

To enable text-to-speech capabilities using the say MCP server, add the following configuration:

For Cline (VSCode Extension)

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"]
    }
  }
}
For Claude Desktop

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 rate
  • list_voices: List all available text-to-speech voices

License

MIT License - See LICENSE file for details

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.