Skip to content
Vendia

Getting Started with Vendia MCP Server

This guide will walk you through setting up Vendia MCP Server to work with AI applications like Claude, enabling it to access your Vendia data in real-time.

Prerequisites

Before you begin, ensure you have:

  1. Active Vendia Uni: A running Uni with the data you want to make accessible to AI applications
  2. Vendia Account Access: Permissions to access your Uni settings and resources
  3. AI Application: Claude Desktop or another MCP-compatible AI application

Claude and other modern MCP clients now support remote MCP connections directly, making setup much simpler.

Step 1: Locate Your MCP Server URL

  1. Navigate to your Vendia Uni dashboard
  2. Go to Uni Settings → Resources
  3. Find your “UNI MCP Server URL” - you’ll need this for configuration
  4. Copy the URL

Step 2: Add Remote MCP Server in Claude

  1. Open Claude Desktop
  2. Navigate to the MCP integrations section
  3. Add your Vendia MCP Server URL directly
  4. When you first use the integration, you’ll be prompted to authenticate via OAuth

For detailed instructions, see Claude’s guide on custom integrations using remote MCP.

Step 3: Authenticate and Use

Once configured, when you try to use the Vendia integration:

  1. You’ll be directed to authenticate with your Vendia credentials
  2. Complete the OAuth flow in your browser
  3. Return to Claude to start using your Vendia data

Option 2: Local Proxy Connection (Legacy)

For older MCP clients that don’t support remote connections, you can use a local proxy. This requires Node.js and npm installed on your machine.

Prerequisites for Local Proxy

Node.js and npm: Install Node.js (version 22 LTS or later) from the official website or via command line:

  • macOS/Linux:

    Terminal window
    curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs

  • Windows:

    Terminal window
    winget install OpenJS.NodeJS.LTS

Configure Local Proxy

  1. Locate your MCP Server URL (same as Step 1 above)

  2. Edit your client’s configuration file to use the npx proxy:

    {
      "mcpServers": {
        "vendia": {
          "command": "npx",
          "args": ["-y", "mcp-remote", "YOUR_UNI_MCP_SERVER_URL"]
        }
      }
    }

    Note: Replace "YOUR_UNI_MCP_SERVER_URL" with your actual MCP Server URL copied from your Vendia Uni dashboard.

  3. Restart your MCP client and authenticate when prompted

Option 3: Programmatic Access for AI Applications

For building AI applications that need programmatic access to the Vendia MCP Server, use API credentials with OAuth2 client credentials flow.

Step 1: Create API Credentials

  1. Follow the API Authentication guide to create API credentials
  2. Note your client_id and client_secret

Step 2: Exchange Credentials for Access Token

Your application needs to exchange the credentials for a JWT token:

// Example: Exchange credentials for access token
const response = await fetch("https://auth.share.vendia.com/token", {
  method: "POST",
  headers: {
    "Content-Type": "application/x-www-form-urlencoded",
  },
  body: new URLSearchParams({
    grant_type: "client_credentials",
    client_id: "YOUR_CLIENT_ID", // Replace with your actual client ID
    client_secret: "YOUR_CLIENT_SECRET", // Replace with your actual client secret
  }),
});


const { access_token } = await response.json();

Step 3: Configure AI SDK with Bearer Token

Configure your AI SDK to connect to the MCP server with the authorization header:

// Example configuration using the OpenAI SDK
const resp = await client.responses.create({
  model: "gpt-4.1",
  tools: [
    {
      type: "mcp",
      server_label: "Vendia",
      require_approval: "never",
      server_url: "YOUR_UNI_MCP_SERVER_URL",
      headers: {
        Authorization: `Bearer ${vendiaAccessToken.access_token}`,
      },
    },
  ],
  input: "Tell me about my tables in Vendia",
});

For complete examples and token refresh logic, see the API Authentication documentation.

Verify Your Connection

Regardless of which method you used, you can verify the connection by:

  • Asking your AI application to list available GraphQL types
  • Running a simple query against your data
  • Checking file access capabilities

For a complete list of available tools and capabilities, see Overview - Available Tools.

Troubleshooting

”Vendia” Option Not Appearing

  • Ensure you’ve completely restarted Claude Desktop
  • Verify your configuration file syntax is correct (valid JSON)
  • Check that the MCP Server URL is accessible

Authentication Issues

  • Verify your Vendia credentials are correct
  • Ensure your account has access to the specified Uni
  • Check that popup blockers aren’t preventing the authentication window

Connection Errors

  • Confirm the MCP Server URL is correct and accessible
  • Verify your network connection allows access to the Vendia servers
  • Check if corporate firewalls are blocking the connection

Data Access Issues

  • Ensure your Vendia account has appropriate permissions for the data you’re trying to access
  • Verify the Uni contains the expected data and schema
  • Check that your node has the necessary access rights

Next Steps

Now that you have Vendia MCP Server configured with Claude, you can:

  1. Explore Your Data: Ask Claude to show you what data types and structures are available
  2. Run Queries: Execute both operational (GraphQL) and analytical (SQL) queries
  3. Build Applications: Use Claude to help develop applications that leverage your Vendia data
  4. Create Reports: Generate insights and reports based on your data

Need Help?

If you encounter issues during setup or have questions about using Vendia MCP Server:

  • Review our FAQ for common questions
  • Check the Overview for detailed feature explanations
  • Contact Vendia Support for technical assistance

The Vendia team is here to help you make the most of AI-powered access to your distributed data!