Skip to content
Vendia

Connect Your AI Agent to Vendia's 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 data in real-time.

Choose Your Setup Path

Select the setup path that matches your Vendia service:

Free Tier Users

If you’re using Vendia’s MCP as a Service Free Tier, jump to Free Tier Setup below.

Enterprise Tier Users

If you’re using the Vendia Enterprise Tier with Unis, continue to Enterprise Tier Setup below.

Free Tier Setup

If you’re using Vendia’s MCP as a Service Free Tier, follow this streamlined setup process designed specifically for individual users.

For more information about Free Tier features, limitations, and frequently asked questions, see the MCP as a Service Free Tier FAQ.

Free Tier Prerequisites

  • Amazon S3 bucket(s) with the data you want to make accessible to AI applications
  • AWS account access to create cross-account IAM roles
  • MCP-Compatible AI Application such as Claude Desktop, Claude Web, or other MCP clients

Free Tier Setup Steps

  1. Get MCP Server URL: Your MCP server URL is provided in the Vendia Free Tier console. Copy this URL - you’ll need it for your AI application.

  2. Configure AI Application: Add the MCP server URL to your AI application following the steps in Option 1: Direct Remote MCP Connection below.

Enterprise Tier Setup

If you’re using the Vendia Enterprise Tier, follow this setup process for Unis and nodes.

Enterprise Tier Prerequisites

  • Active Vendia Uni: A running Uni with the data you want to make accessible to AI applications
  • Vendia Account Access: Permissions to access your Uni settings and resources
  • MCP-Compatible AI Application: Such as Claude, OpenAI-compatible applications, or other MCP-enabled AI tools

Enterprise Tier Setup Steps

  1. Locate Your MCP Server URL

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

  2. Configure Your AI Application: Choose from the available connection options below using your Uni MCP Server URL.

Modern MCP clients support remote MCP connections directly, making setup much simpler across different AI applications.

Connecting Your AI Application

Add your Vendia MCP Server URL to your preferred AI application:

Claude Desktop

  1. Open Claude Desktop
  2. Go to Settings > Connectors in the application menu
  3. In the “Connectors” section, click “Add custom connector” at the bottom
  4. Enter your Vendia MCP Server URL in the server URL field
  5. Provide a name for the connector (e.g., “Vendia”)
  6. Click “Add” to finish configuring your connector
  7. To use the connector, click the “Search and tools” button in the lower left of your chat interface
  8. Find your Vendia connector and click “Connect” to authenticate via OAuth
  9. After authentication, enable the specific tools you want to use from the connector

For detailed instructions, see Claude’s official MCP integration guide.

Claude Web App (claude.ai)

For Individual Users (Pro and Max plans):

  1. Go to claude.ai and sign in to your account
  2. Navigate to Settings > Connectors (or go directly to claude.ai/settings/connectors)
  3. In the “Connectors” section, click “Add custom connector” at the bottom
  4. Enter your Vendia MCP Server URL in the server URL field
  5. Provide a name for the connector (e.g., “Vendia”)
  6. Click “Add” to finish configuring your connector

For Workspace Users (Team and Enterprise plans):

  1. Organization Setup (Primary Owner/Owner only):

    • Go to claude.ai/settings/connectors
    • Toggle to “Organization connectors” at the top of the page
    • In the “Connectors” section, click “Add custom connector” at the bottom
    • Enter your Vendia MCP Server URL in the server URL field
    • Provide a name for the connector (e.g., “Vendia”)
    • Click “Add” to finish configuring your connector

  2. Individual User Setup:

    • Navigate to Settings > Connectors
    • Find the Vendia connector added by your organization
    • In any conversation, click the “Search and tools” button (or use @ in the message input)
    • Find your Vendia connector and click “Connect” to authenticate via OAuth
    • After authentication, enable the specific tools you want to use from the connector

For All Users:

  1. In any conversation, click the “Search and tools” button (or use @ in the message input)
  2. Find your Vendia connector and click “Connect” to authenticate via OAuth
  3. After authentication, enable the specific tools you want to use from the connector

OpenAI Compatible Applications

For applications using OpenAI’s API or compatible interfaces, configure the MCP server in your application settings or SDK initialization. See OpenAI’s MCP documentation for specific implementation details.

Other MCP-Compatible Applications

Most MCP-compatible applications follow similar patterns:

  1. Locate the MCP or integrations settings
  2. Add a new remote MCP server
  3. Enter your Vendia MCP Server URL
  4. Configure authentication when prompted

For application-specific guides, consult your AI application’s documentation on Model Context Protocol integration.

Authentication and Usage

Once you’ve configured your AI application with your Vendia MCP Server URL, here’s how to authenticate and start using it:

  1. First Use: When you first try to use the Vendia integration in your AI application, you’ll be directed to authenticate with your Vendia credentials
  2. OAuth Flow: Complete the OAuth authentication flow in your browser
  3. Return to AI App: Return to your AI application to start using your Vendia data

Your AI application will now have access to your Vendia data and can help you query, analyze, and work with your information.

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 in Enterprise Tier Setup 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.

AI Application Setup Guides

For detailed setup instructions specific to your AI application:

Custom Applications

If you’re building a custom AI application, refer to the Model Context Protocol specification for implementation details.

Verify Your Connection

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

Free Tier Connection Verification

  • Asking your AI application to list available files in your connected S3 buckets
  • Testing file access by requesting content from a specific file
  • Checking that storage connections are working properly

Enterprise Tier Connection Verification

  • Asking your AI application to list available GraphQL types
  • Running a simple operational (GraphQL) query against your Uni data
  • Testing analytical (SQL) capabilities on your data
  • Testing Vendia Files access and file operations
  • Testing file access from connected S3 buckets via Storage Connections

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

Troubleshooting

”Vendia” Option Not Appearing

  • Ensure you’ve completely restarted your AI application (e.g., 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

Storage Connection Issues (both tiers):

  • Verify your cross-account IAM role has the correct S3 permissions
  • Check that your storage connection configuration is correct
  • Ensure your S3 bucket contains accessible files

Enterprise Tier Uni Data 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 your AI application, you can:

Free Tier Next Steps

  1. Set Up Storage Connections: Configure access to your S3 buckets using the Storage Connections guide
  2. Explore Your Files: Ask your AI application to list and access files in your connected S3 buckets
  3. Analyze Content: Use your AI application to read, analyze, and work with text, image, and PDF files
  4. Monitor Usage: Track file access and usage through the Vendia Free Tier console

Enterprise Tier Next Steps

  1. Explore Your Unis: Ask your AI application to show you what data types and structures are available in your Unis
  2. Run Operational Queries: Execute GraphQL queries for real-time data operations and mutations
  3. Run Analytical Queries: Execute SQL queries for data analysis and reporting
  4. Work with Vendia Files: Upload, manage, and access files stored directly in your Vendia Unis
  5. Set Up Storage Connections: Configure access to external S3 buckets using the Storage Connections guide
  6. Build Applications: Use your AI application to help develop applications that leverage operational data, analytical insights, Vendia Files, and S3 data
  7. Create Reports: Generate comprehensive insights and reports based on your structured and unstructured data

Need Help?

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

Free Tier Support

Enterprise Tier Support

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