UBOS Asset Marketplace: Snappy MCP Server with Xano Integration

In the rapidly evolving landscape of AI, the ability to seamlessly integrate Large Language Models (LLMs) with external data sources and tools is paramount. The UBOS Asset Marketplace offers a solution tailored for this need: a snappy MCP (Model Context Protocol) Server with seamless Xano database integration. This server, built on Cloudflare Workers, empowers developers to manage tools, track sessions, and handle OAuth authentication efficiently.

What is an MCP Server?

At its core, an MCP Server acts as a crucial bridge, standardizing how applications provide context to LLMs. This standardized protocol ensures that AI models can access and interact with external resources in a controlled and predictable manner. Without such a protocol, integrating AI models can become a complex and error-prone task.

Key Features:

• Xano Integration: Leverages Xano as a robust backend for tool management, session tracking, OAuth authentication, and logging. This simplifies the process of managing and securing access to your AI tools.
• Cloudflare Workers: Built on Cloudflare Workers for scalability, reliability, and global availability. This ensures your MCP Server can handle a high volume of requests with low latency.
• Tool Management: Define tools in Xano’s ____mcp_tools table, and they are automatically registered in the MCP Server, streamlining the tool management process.
• Session Tracking: Tracks all MCP sessions in the ___mcp_sessions table, providing valuable insights into tool usage and user behavior.
• OAuth Authentication: Securely stores OAuth tokens and states in Xano’s ___oauth_tokens and ___oauth_states tables, ensuring secure access to protected resources.
• Comprehensive Logging: Logs all MCP requests in the ___mcp_logs table, aiding in debugging and auditing.

Use Cases:

1. Enhancing LLM Capabilities: By connecting LLMs to external databases, APIs, and other tools, the MCP Server enables AI models to perform more complex and context-aware tasks. For instance, an LLM can use a math tool to perform calculations or access real-time data to provide accurate responses.
2. Automating Workflows: The MCP Server can be used to automate workflows by orchestrating the execution of multiple tools in a specific sequence. This can be particularly useful in scenarios where human intervention is minimal.
3. Building AI Agents: The MCP Server provides a foundation for building AI agents that can interact with the real world. These agents can use tools to perform actions, such as sending emails, updating databases, or controlling IoT devices.
4. Secure Data Access: The OAuth authentication feature ensures that LLMs can securely access protected resources, such as user data or proprietary APIs.
5. Centralized Tool Management: The Xano integration provides a centralized platform for managing all AI tools, making it easier to add, remove, and update tools as needed.

Getting Started:

To get started with the UBOS Asset Marketplace MCP Server, follow these steps:

1. Local Development: Clone the repository, install dependencies, and configure your Xano API key.
2. MCP Inspector: Connect the MCP Inspector to your local server to explore the API and test your tools.
3. Claude Integration: Connect Claude Desktop to your local MCP server to leverage the power of LLMs in your AI workflows.
4. Xano Setup: Create a Xano project with the required tables and API endpoints.
5. Cloudflare Deployment: Deploy the MCP Server to Cloudflare for production use.

Detailed Instructions:

• Local Development:

  bash

  clone the repository

  git clone https://github.com/roboulos/remote-mcp-server.git

  install dependencies

  cd remote-mcp-server npm install

  Configure Xano API Key

  Add your Xano API key to wrangler.jsonc in the XANO_API_KEY variable

  run locally

  npm run dev

  You should be able to open http://localhost:8787/ in your browser.

• Connecting the MCP Inspector:

  To explore your new MCP API, you can use the MCP Inspector.

  • Start it with npx @modelcontextprotocol/inspector
  • Within the inspector, switch the Transport Type to SSE and enter http://localhost:8787/sse as the URL of the MCP server to connect to, and click “Connect”
  • You will navigate to a (mock) user/password login screen. Input any email and pass to login.
  • You should be redirected back to the MCP Inspector, and you can now list and call any defined tools!

• Connecting Claude Desktop:

  Follow Anthropic’s Quickstart, and within Claude Desktop, go to Settings > Developer > Edit Config to find your configuration file.

  Open the file in your text editor and replace it with this configuration:

  { “mcpServers”: { “math”: { “command”: “npx”, “args”: [ “mcp-remote”, “http://localhost:8787/sse” ] } } }

  This will run a local proxy and let Claude talk to your MCP server over HTTP.

  When you open Claude, a browser window should open and allow you to log in. You should see the tools available in the bottom right. Given the right prompt, Claude should ask to call the tool.

• Xano Integration Details:

  This MCP server uses Xano as its backend for:

  1. Tool Management: Define tools in Xano’s ____mcp_tools table, and they will be automatically registered in the MCP server.
  2. Session Tracking: All MCP sessions are tracked in the ___mcp_sessions table.
  3. OAuth Authentication: OAuth tokens and states are stored in Xano’s ___oauth_tokens and ___oauth_states tables.
  4. Logging: All MCP requests are logged in the ___mcp_logs table.

  To set up Xano, you need to:

  1. Create a Xano project with the required tables (see database schema).
  2. Create API endpoints for:
     • /api/tools - GET - List all tools
     • /api/tools/execute/{tool_name} - POST - Execute a specific tool
     • /api/sessions - POST - Create a new session
     • /api/sessions/update-activity - PUT - Update session activity
     • /api/oauth/tokens - POST - Store OAuth tokens
     • /api/oauth/tokens/{user_id}/{provider} - GET - Get OAuth tokens
     • /api/oauth/states - POST - Store OAuth states
     • /api/oauth/states/{state} - GET - Validate OAuth states
     • /api/logs - POST - Log MCP requests

• Cloudflare Deployment:

  1. npx wrangler kv namespace create OAUTH_KV
  2. Follow the guidance to add the kv namespace ID to wrangler.jsonc
  3. Add your Xano API key to the XANO_API_KEY variable in wrangler.jsonc
  4. npm run deploy

Debugging Tips:

• Restart Claude if anything goes wrong.

• Try connecting directly to your MCP server on the command line with the following command:

  bash npx mcp-remote http://localhost:8787/sse

• In some rare cases, it may help to clear the files added to ~/.mcp-auth:

  bash rm -rf ~/.mcp-auth

UBOS Platform: The Future of AI Agent Development

The UBOS platform is a full-stack AI Agent Development Platform designed to bring AI Agents to every business department. It offers a comprehensive suite of tools and features to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems. By leveraging the UBOS platform, you can accelerate the development and deployment of AI-powered solutions and gain a competitive edge in the AI era.

Key Benefits of Using UBOS:

• Accelerated Development: UBOS provides pre-built components and templates that speed up the development process.
• Seamless Integration: UBOS seamlessly integrates with existing enterprise systems and data sources.
• Scalability and Reliability: UBOS is built on a scalable and reliable infrastructure, ensuring your AI Agents can handle a high volume of requests.
• Security and Compliance: UBOS provides robust security features and compliance certifications, ensuring your AI Agents are secure and compliant with industry regulations.
• Centralized Management: UBOS provides a centralized platform for managing all AI Agents, making it easier to monitor, update, and deploy your AI-powered solutions.

In conclusion, the UBOS Asset Marketplace MCP Server with Xano integration is a powerful tool for connecting LLMs to external data sources and tools. By leveraging this solution, you can enhance the capabilities of your AI models, automate workflows, and build intelligent AI Agents. Combined with the UBOS platform, you have a complete solution for AI Agent development and deployment, empowering you to drive innovation and transform your business.