UPLO 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.

Quick Start

Claude Desktop

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 Code

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"

Cursor

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"
      }
    }
  }
}

Windsurf

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"
      }
    }
  }
}

Self-Hosted (Docker)

Run the MCP server alongside your own Supabase instance:

docker compose up -d

See docker-compose.yml for the full configuration.

Example Queries

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 next 30 days"
• "What systems does the engineering team use?"

Industry Examples

• Legal
• Healthcare
• Finance
• Engineering
• Government

MCP Tools Available

Tool	Description
search_knowledge	Semantic search across extracted knowledge
search_with_context	GraphRAG: vector search + entity resolution + edge traversal
export_org_context	Full organizational context snapshot
get_directives	Strategic priorities and directives
find_knowledge_owner	Find subject matter experts
propose_update	Suggest knowledge base updates
report_knowledge_gap	Flag missing information
flag_outdated	Mark stale entries
get_identity_context	Agent identity and org context
log_conversation	Log agent conversations for audit
export_workspace	Export digital twin as workspace files

About UPLO

UPLO is the organizational digital twin for AI. Ingest documents (1,400+ formats), extract structured knowledge (195 schemas across 40 industry packs), build organizational context layers, and expose it all via MCP server with GraphRAG.

• Website: uplo.ai
• Documentation: docs.uplo.ai
• MCP Server: @agentdocs1/mcp-server

License

MIT