Bold BI MCP Tool User Guide for AI Assistants

Overview

The Bold BI MCP Tool is a Model Context Protocol (MCP) server that lets AI assistants and MCP-compatible applications interact with Bold BI through structured tools.

Model Context Protocol (MCP) is a standardized protocol that allows AI assistants to connect to external systems through structured tools over a Streamable HTTP endpoint. Instead of calling Bold BI’s REST API directly, a user can ask a question in natural language, and the AI assistant invokes the matching MCP tool to retrieve information or perform an action on their behalf.

The Bold BI MCP Tool exposes more than 50 tools across dashboards, data sources, users, groups, schedules, slideshows, pinboards, items, categories, published content, and webhooks. These are read-and-operate tools covering discovery, inspection, and export of Bold BI content.

Using an MCP-compatible client, users can:

• Discover available dashboards and content.
• Retrieve dashboard, data source, user, and group information.
• Export dashboards and data sources.
• Review permissions and access history.
• Monitor schedules and governance information.
• Integrate Bold BI operations into AI-powered workflows.

How the MCP Tool Works

The Bold BI MCP Tool acts as a bridge between an MCP-compatible client and a Bold BI site.

1. The user submits a request through an AI assistant or MCP-compatible client.
2. The MCP client sends the request to the Bold BI MCP service.
3. The MCP service authenticates the request using the token supplied in the Authorization header.
4. The MCP service routes the request to the target Bold BI site specified in the ServiceURL header.
5. The Bold BI site API executes the requested operation.
6. The result is returned to the MCP service.
7. The MCP service returns the response to the MCP client.
8. The AI assistant presents the result to the user.

Components

Prerequisites

Before configuring the Bold BI MCP Tool, make sure the following are in place.

Bold BI requirements

• A reachable Bold BI site Caller URL.
• A valid Bold BI user account or service account.
• A valid Bold BI authentication token (Bearer or Basic).
• Permissions required for the operations you want to perform.

Required connection information

• Bold BI MCP endpoint URL.
• Bold BI site API URL.
• A valid authentication token.

Network requirements

• Outbound HTTPS access to https://mcp.boldbi.com/api/mcp.
• Firewall rules that don’t block access to the MCP endpoint.
• Proxy configurations that allow traffic to the hosted service.
• The target Bold BI site must be reachable from the MCP service.

MCP client requirements

Your client must support:

• Model Context Protocol (MCP)
• Streamable HTTP transport
• Custom HTTP headers

Authentication

The MCP service forwards the Authorization header it receives to the Bold BI REST API. Authenticate requests using a Bold BI API key.

Generate an API key form your Bold BI profile. For instructions, see Generate a Bold BI API Key.

Required headers

Configure an MCP Client

Use this MCP service endpoint:

https://mcp.boldbi.com/api/mcp

Every tool call that reaches Bold BI must include the Authorization and ServiceURL headers described above.

Example configuration using authorization token

{
  "servers": {
    "boldbi": {
      "type": "http",
      "url": "https://mcp.boldbi.com/api/mcp",
      "headers": {
        "Authorization": "${BOLDBI_TOKEN}",
        "ServiceURL": "http://your-boldbi-host/bi/api/site/site1"
      }
    }
  }
}

Replace http://your-boldbi-host/bi/api/site/site1 with your own Bold BI site’s API base URL.

Connect Bold BI MCP Server in External Clients

You can connect the Bold BI MCP server to external AI clients such as Claude Desktop to access Bold BI MCP tools directly within the client application.

Configure MCP in Claude Desktop

Step 1: Open the configuration file

1. Open the Claude Desktop application.
2. Click your Profile icon in the bottom-left corner and select Settings.

3. Navigate to the Developer tab.

4. Under Local MCP Servers, click Edit Config. Open the claude_desktop_config.json file in your text editor.

Step 2: Add the MCP server configuration

Add the following MCP server configuration:

{
  "mcpServers": {
    "syncfusion_kpis": {
      "command": "C:\\Program Files\\nodejs\\npx.cmd",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.boldbi.com/api/mcp",
        "--transport",
        "http-only",
        "--header",
        "Authorization:${BOLDBI_TOKEN}",
        "--header",
        "ServiceURL:${BOLDBI_SERVICE_URL}"
      ],
      "env": {
        "BOLDBI_TOKEN": "<YOUR_BOLD_BI_TOKEN>",
        "BOLDBI_SERVICE_URL": "https://kpis.syncfusion.com/bi/api/site/cmo-cro1"
      }
    }
  }
}

NOTE:

• In the env section, replace <YOUR_BOLD_BI_TOKEN> with a valid Bold BI access token (API key).
• In the env section, update BOLDBI_SERVICE_URL with your Bold BI site API URL (for example, https://<your-domain>/bi/api/site/<site-identifier>).
• Ensure that Node.js is installed and that the specified npx.cmd path is accessible on your machine. You can find your path by running where npx in the Command Prompt (for example, C:\Program Files\nodejs\npx.cmd).

Step 3: Save and restart

1. Save the claude_desktop_config.json file.
2. Exit the Claude Desktop application completely. On Windows, click the hidden icons arrow (^) in the taskbar system tray, right-click the Claude icon, and select Exit.
3. Reopen the Claude Desktop application.

Step 4: Verify the MCP server

1. Navigate to Profile → Settings → Developer.
2. Under Local MCP Servers, verify that the syncfusion_kpis server status is Running.

3. In the chat interface, open the Connectors (or MCP Tools) menu to verify that syncfusion_kpis is listed. Select it to review the available Bold BI MCP tools, where you can choose to allow them, require approval, or block specific tools.

4. Once connected, prompt Claude in natural language to explore dashboards, inspect data sources, and interact with Bold BI analytics.

Available MCP Tools

The Bold BI MCP service exposes more than 50 tools, organized into 11 functional categories.

Dashboard tools (16)

Dashboard settings tools (2)

Category tools (2)

Data source tools (8)

User tools (8)

Group tools (5)

Item and pinboard tools (6)

Published content tools (2)

Schedule tools (2)

Slideshow tools (2)

Webhook tools (1)

Common Use Cases

Explore and summarize dashboards

Example prompts: “List all dashboards.” · “Get the widgets for this dashboard.” · “Export the Sales Analysis dashboard as a PDF.”

Tools used: dashboard_list, dashboard_get, dashboard_widgets_list, dashboard_view_list, dashboard_export

Inspect dashboard output and downloads

Example prompts: “Show the access history for this dashboard.” · “Prepare a downloadable copy of the export.” · “Check the status of a dashboard upload.”

Tools used: dashboard_access_history_get, dashboard_download_prepare, dashboard_download_status_get, dashboard_upload_status_get, dashboard_draft_list, deployment_dashboard_list

Share content with users and groups

Example prompts: “Show which dashboards are accessible by the Operations group.” · “List the groups a user belongs to.” · “Show the permissions a user has on dashboards.”

Tools used: group_list, group_get, group_users_list, group_permissions_get, user_list, user_get, user_groups_list, user_permissions_get, dashboard_by_group_permissions_list, dashboard_permissions_get

Manage data sources

Example prompts: “List all data sources and identify which dashboards depend on each one.” · “Export this data source as CSV with selected columns.” · “Show recent activity on a data source.”

Tools used: datasource_list, datasource_get, datasource_columns_list, datasource_linked_dashboards_list, datasource_export, datasource_activity_get

Provision and audit users

Example prompts: “Look up a user and list the groups they belong to.” · “Inspect the attributes assigned to a user or group.” · “Download the CSV template for bulk user import and check job status.”

Tools used: user_list, user_get, user_attributes_get, user_groups_list, user_permissions_get, group_attributes_get, user_csv_template_download, user_import_job_status_get, user_import_failed_list

Schedule and monitor reports

Example prompts: “List the schedules configured for this site.” · “Get the details of a specific schedule.”

Tools used: schedule_list, schedule_get

Audit activity and governance

Example prompts: “Show dashboard activity for the last 7 days.” · “Show recent access history for a dashboard.” · “Summarize data source activity for compliance review.”

Tools used: dashboard_access_history_get, datasource_activity_get, dashboard_public_list, dashboard_favorite_list

Discover content, pinboards, and published sites

Example prompts: “List pinboards available on this site.” · “Find an item by name to avoid duplicates.” · “List published items and the configured publish sites.”

Tools used: item_list, item_get, item_name_exists_check, pinboard_list, pinboard_get, pinboard_name_exists_check, published_item_list, external_publish_site_list, slideshow_list, slideshow_get, webhook_list

Inspect dashboard settings

Example prompts: “Show the current global dashboard settings.”

Tools used: dashboard_settings_get, category_list, category_get

Troubleshooting

Security and Best Practices

When using the Bold BI MCP Tool:

• Store authentication tokens in environment variables or a secure secret-management solution.
• Never commit tokens or credentials to source control.
• Use dedicated service accounts for automation scenarios whenever possible.
• Follow the principle of least privilege: grant only the permissions required for the operations being performed.
• Use HTTPS for all communication with the MCP service.
• Avoid including confidential business information or credentials in prompts.
• Rotate authentication tokens periodically, according to your organization’s security policy.