ScavioScavio

MCP Integration

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. Scavio runs an MCP server that gives any compatible client access to 9 tools covering Google Search, Amazon, Walmart, and YouTube. Setup takes under 2 minutes.

Prerequisites

  1. Get your API key at dashboard.scavio.dev
  2. Replace YOUR_SCAVIO_API_KEY in the examples below with your actual key

Claude Code

Run this single command in your terminal:

Bash
claude mcp add --transport http scavio https://mcp.scavio.dev/mcp \
  --header "x-api-key: YOUR_SCAVIO_API_KEY"

To add it to a shared project config (checked into version control), use --scope project:

Bash
claude mcp add --transport http --scope project scavio https://mcp.scavio.dev/mcp \
  --header "x-api-key: YOUR_SCAVIO_API_KEY"

Alternatively, add the JSON config directly:

Bash
claude mcp add-json scavio '{
  "type": "http",
  "url": "https://mcp.scavio.dev/mcp",
  "headers": {
    "x-api-key": "YOUR_SCAVIO_API_KEY"
  }
}'

Verify the connection:

Bash
claude mcp list

Claude Desktop

  1. Open Claude Desktop
  2. Go to Settings > Developer > Edit Config
  3. Add Scavio to your claude_desktop_config.json:
JSON
{
  "mcpServers": {
    "scavio": {
      "type": "http",
      "url": "https://mcp.scavio.dev/mcp",
      "headers": {
        "x-api-key": "YOUR_SCAVIO_API_KEY"
      }
    }
  }
}
  1. Save and restart Claude Desktop

Config file location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Cursor

  1. Open Cursor and go to Settings > Tools & MCP
  2. Click + Add New MCP Server
  3. Select type HTTP and enter:
    • Name: scavio
    • URL: https://mcp.scavio.dev/mcp
    • Headers: x-api-key: YOUR_SCAVIO_API_KEY
  4. Click Save

Or manually edit .cursor/mcp.json in your project root (or ~/.cursor/mcp.json for global):

JSON
{
  "mcpServers": {
    "scavio": {
      "type": "http",
      "url": "https://mcp.scavio.dev/mcp",
      "headers": {
        "x-api-key": "YOUR_SCAVIO_API_KEY"
      }
    }
  }
}

Windsurf

  1. Open Windsurf and click the hammer icon in Cascade
  2. Click Configure to open the MCP config
  3. Add Scavio to ~/.codeium/windsurf/mcp_config.json:
JSON
{
  "mcpServers": {
    "scavio": {
      "type": "http",
      "url": "https://mcp.scavio.dev/mcp",
      "headers": {
        "x-api-key": "YOUR_SCAVIO_API_KEY"
      }
    }
  }
}
  1. Save the file and refresh Windsurf

VS Code (GitHub Copilot)

  1. Create .vscode/mcp.json in your project root:
JSON
{
  "servers": {
    "scavio": {
      "type": "http",
      "url": "https://mcp.scavio.dev/mcp",
      "headers": {
        "x-api-key": "YOUR_SCAVIO_API_KEY"
      }
    }
  }
}
  1. Open the Command Palette (Ctrl+Shift+P / Cmd+Shift+P)
  2. Run MCP: List Servers to verify the connection

For global setup, add the same config to your VS Code user settings under mcp.servers.

ChatGPT

ChatGPT supports remote MCP servers through its Apps & Connectors feature:

  1. Go to ChatGPT Settings > Apps & Connectors
  2. Click Add custom connector
  3. Enter the MCP server URL: https://mcp.scavio.dev/mcp
  4. Configure authentication with your API key
  5. Save and start using Scavio tools in your chats

ChatGPT MCP support requires a Plus or Team plan and may require OAuth configuration depending on your setup.

Cline (VS Code Extension)

  1. Open VS Code with Cline installed
  2. Click the MCP Servers icon in the Cline sidebar
  3. Click Configure MCP Servers
  4. Add Scavio to the config:
JSON
{
  "mcpServers": {
    "scavio": {
      "type": "http",
      "url": "https://mcp.scavio.dev/mcp",
      "headers": {
        "x-api-key": "YOUR_SCAVIO_API_KEY"
      }
    }
  }
}
  1. Save and Cline will auto-detect the new server

Zed Editor

  1. Open Settings (Cmd+,)
  2. Navigate to the Assistant section
  3. Add Scavio under MCP servers:
JSON
{
  "assistant": {
    "mcp_servers": {
      "scavio": {
        "type": "http",
        "url": "https://mcp.scavio.dev/mcp",
        "headers": {
          "x-api-key": "YOUR_SCAVIO_API_KEY"
        }
      }
    }
  }
}

Any MCP-Compatible Client

Scavio works with any tool that supports the Model Context Protocol. The universal config:

JSON
{
  "type": "http",
  "url": "https://mcp.scavio.dev/mcp",
  "headers": {
    "x-api-key": "YOUR_SCAVIO_API_KEY"
  }
}
DetailValue
TransportHTTP (Streamable HTTP)
URLhttps://mcp.scavio.dev/mcp
AuthenticationAPI key via x-api-key header

Available Tools

Once connected, your AI assistant can use these 9 tools:

ToolDescription
search_googleWeb search with structured results, news, images, maps, and knowledge graph
search_amazonSearch Amazon product listings with price and sort filters
get_amazon_productGet full Amazon product details by ASIN
search_walmartSearch Walmart product listings with price and delivery filters
get_walmart_productGet full Walmart product details by product ID
search_youtubeSearch YouTube videos, channels, and playlists
get_youtube_metadataGet video metadata (title, views, likes, duration)
get_youtube_transcriptGet full timestamped video transcripts
get_usageCheck your credit balance and plan details

Troubleshooting

Server not connecting?

  • Verify your API key is correct and active
  • Check your credits with get_usage or at dashboard.scavio.dev
  • Ensure the URL is exactly https://mcp.scavio.dev/mcp (no trailing slash)

Tools not showing up?

  • Restart your AI client after adding the config
  • Check for JSON syntax errors in your config file
  • Confirm the MCP server appears as "connected" in your client's MCP settings

Next Steps