Deploying the Zoho Analytics MCP Server using Docker gives you a self-contained, reproducible environment that works consistently across macOS, Windows, and Linux. This approach avoids local runtime conflicts and dependency issues, making it a reliable choice for individual developers and teams who want each user to run their own local server instance.

System Requirements

Docker must be installed on the machine running the MCP server. The recommended Docker solution varies by operating system:

• macOS: Docker Desktop, Colima, or Rancher Desktop
• Windows: Docker Desktop or Rancher Desktop
• Linux: Docker Engine, Podman Desktop, or Colima

Step 1: Pull the Docker Image

Download the official Zoho Analytics MCP Server image from Docker Hub by running the following command:

docker pull zohoanalytics/mcp-server:latest

Step 2: Obtain OAuth Credentials

The MCP server authenticates with Zoho Analytics using OAuth credentials. Obtain these from the Zoho Developer Console:

1. Open the Zoho Developer Console. Navigate to the console and start creating a new application.
2. Create a Self-Client application. This type is suitable for local server deployments where each user manages their own credentials.
3. Enable the Zoho Analytics API scope. Select the appropriate scope so the server can access your Analytics data.
4. Generate a refresh token. Save the Client ID, Client Secret, and Refresh Token — all three are required.

Required Environment Variables

Optional Configuration Variables

These variables have sensible defaults but can be adjusted for your environment: QUERY_DATA_RESULT_ROW_LIMITS (default: 20), QUERY_DATA_POLLING_INTERVAL (default: 4 seconds), QUERY_DATA_QUEUE_TIMEOUT (default: 120 seconds), QUERY_DATA_QUERY_EXECUTION_TIMEOUT (default: 30 seconds), WORKSPACE_RESULT_LIMIT (default: 20), and VIEW_RESULT_LIMIT (default: 20).

Step 3: Configure Your MCP Client

With the image pulled and credentials to hand, add the server to your MCP client's configuration. The approach varies slightly by client.

Claude Desktop

Open Claude Desktop, navigate to Settings > Developer > Edit Config, and add the following entry, substituting your actual credential values:

{
  "mcpServers": {
    "ZohoAnalyticsMCP": {
      "command": "docker",
      "args": [
        "run",
        "-e", "ANALYTICS_CLIENT_ID=<your-client-id>",
        "-e", "ANALYTICS_CLIENT_SECRET=<your-client-secret>",
        "-e", "ANALYTICS_REFRESH_TOKEN=<your-refresh-token>",
        "-e", "ANALYTICS_ORG_ID=<your-org-id>",
        "-e", "ANALYTICS_MCP_DATA_DIR=<data-dir>",
        "--network=host",
        "-i",
        "--rm",
        "-v", "<data-dir>:<data-dir>",
        "zohoanalytics/mcp-server"
      ]
    }
  }
}

VS Code and Cursor

VS Code uses settings.json and Cursor uses its own MCP settings file. In both cases the Docker command and arguments are identical to those shown above — only the file location and wrapper syntax differ. Consult the documentation for your specific editor for the exact file paths.

Available MCP Tools

The MCP server exposes 23 tools to connected AI clients across four areas: workspace and table management (including create_workspace, create_table, get_workspaces_list), data operations (import_data, export_view, query_data, add_row, update_rows, delete_rows), reporting (create_chart_report, create_pivot_report, create_summary_report, create_aggregate_formula), and utility functions (search_views, get_view_details, delete_view, analyse_file_structure, download_file).

Troubleshooting

• Authentication errors: Verify your OAuth credentials are correct, check that the required API scope is enabled, and confirm the refresh token has not expired.
• Connection issues: Confirm the Docker container is running, validate network connectivity, and check that firewalls are not blocking the connection.
• Data centre errors: Make sure ACCOUNTS_SERVER_URL and ANALYTICS_SERVER_URL match the data centre location of your Zoho organisation.
• File system issues: Verify that the directory specified in ANALYTICS_MCP_DATA_DIR exists, has the correct permissions, and has sufficient disk space.

Support

Zoho Analytics offers 24x5 technical support. Contact the team by email at support@zohoanalytics.com or by telephone: US +1 (888) 900 9646, UK +44 (20) 35647890, Australia +61-2-80662898, India +91 44 6965 6060.