mcp-starter

Get organizational knowledge into your AI coding assistant in 5 minutes.

UPLO is the organizational digital twin for AI — ingest documents, extract structured knowledge, and expose it via MCP.

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "uplo": {
      "command": "npx",
      "args": ["-y", "@agentdocs1/mcp-server"],
      "env": {
        "AGENTDOCS_URL": "https://your-instance.uplo.ai",
        "API_KEY": "your-api-key"
      }
    }
  }
}

See `claude_desktop_config.json` for the full template.

claude mcp add uplo -- npx -y @agentdocs1/mcp-server

Then set your environment variables:

export AGENTDOCS_URL="https://your-instance.uplo.ai"
export API_KEY="your-api-key"

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "uplo": {
      "command": "npx",
      "args": ["-y", "@agentdocs1/mcp-server"],
      "env": {
        "AGENTDOCS_URL": "https://your-instance.uplo.ai",
        "API_KEY": "your-api-key"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "uplo": {
      "command": "npx",
      "args": ["-y", "@agentdocs1/mcp-server"],
      "env": {
        "AGENTDOCS_URL": "https://your-instance.uplo.ai",
        "API_KEY": "your-api-key"
      }
    }
  }
}

Run the MCP server alongside your own Supabase instance:

docker compose up -d

See `docker-compose.yml` for the full configuration.

Once connected, try asking your AI assistant:

• "What is our company's PTO policy?"
• "Who is the expert on data privacy?"
• "What are our Q2 strategic priorities?"
• "Find all contracts expiring in the nex