Tableau MCP Server

How to use

Once the MCP server is running, you interact with it through an MCP client (like Claude Desktop) to perform data access, searches, and administrative tasks. You can ask to list workbooks, views, and data sources, export CSV data from a view, download dashboard images, and retrieve complete datasets. You can also audit permissions, review site statistics, and see usage analytics. Typical usage patterns include: listing content, locating dashboards containing specific metrics, exporting view data as CSV, and auditing who has access to particular workbooks.

This server exposes content as MCP resources you can reference in your workflows, for example workbook metadata and view data in CSV format. Use the available tools to navigate Tableau content and perform admin checks without leaving your Claude workflow.

How to install

Prerequisites you need before installation.

# Prerequisites
Python 3.8+
Claude Desktop installed
Access to Tableau Server or Tableau Cloud
Administrative privileges (for admin tools)

1) Clone the MCP server repository and set up a local environment.

# Clone the repository
git clone https://github.com/hetpatel-11/Tableau-MCP.git
cd Tableau-MCP

# Create virtual environment (recommended)
python -m venv tableau_mcp_env
source tableau_mcp_env/bin/activate  # On Windows: tableau_mcp_env\Scripts\activate

# Install ALL dependencies including MCP SDK
pip install -r requirements.txt

2) Install MCP SDK if needed to ensure compatibility with the MCP framework.

# Option 1: Install MCP SDK directly
pip install mcp>=1.0.0

# Option 2: Install with specific version
pip install mcp==1.0.0

# Option 3: Install from source
pip install git+https://github.com/modelcontextprotocol/python-sdk.git

# Option 4: Force reinstall
pip install --force-reinstall mcp>=1.0.0

3) Verify the installation and readiness of components.

# Test that MCP SDK is properly installed
python -c "import mcp; print('✅ MCP SDK installed successfully')"

# Test Tableau Server Client
python -c "import tableauserverclient as TSC; print('✅ Tableau Server Client ready')"

# Test the server (will run the server in your environment)
python tableau_mcp_server.py --test

4) Configure credentials for Tableau access.

TABLEAU_SERVER_URL=https://your-tableau-server.com
TABLEAU_SITE_ID=your-site-name

# Option 1: Personal Access Token (Recommended)
TABLEAU_TOKEN_NAME=your-token-name
TABLEAU_TOKEN_VALUE=your-token-value

# Option 2: Username/Password (if token is not used)
# TABLEAU_USERNAME=your-username
# TABLEAU_PASSWORD=your-password

5) Set up Claude Desktop to point to the MCP server.

{
  "mcpServers": {
    "tableau-server": {
      "command": "/path/to/Tableau-MCP/start_clean.sh",
      "args": []
    }
  }
}

6) Start the MCP server.

# Make startup script executable
chmod +x start_clean.sh

# Start the server
./start_clean.sh

Additional setup and notes

Configuration details and security best practices.

# Example environment for credentials and permissions
TABLEAU_SERVER_URL=https://your-tableau-server.com
TABLEAU_SITE_ID=your-site-name
TABLEAU_TOKEN_NAME=your-token-name
TABLEAU_TOKEN_VALUE=your-token-value

Security and ownership guidance.

- The server runs locally with your permissions and uses environment variables for authentication. - Personal Access Tokens are recommended for secure access. - Review permissions and site statistics via admin tools to ensure proper access control.

Troubleshooting

Common issues and how to fix them.

- MCP SDK not found or version conflicts: ensure the correct Python version and reinstall the SDK.

- Authentication failed: verify credentials in your environment variables and Tableau access.

- No tools available in Claude: restart Claude Desktop after configuration and confirm dependencies are installed.

list_workbooks

List all available Tableau workbooks

list_views

List views in a specific workbook

get_view_data

Extract CSV data from any view

get_view_image

Get dashboard/view as PNG image

search_content

Search across all Tableau content

list_datasources

List all available data sources

download_datasource

Download complete raw datasets

list_workbook_permissions

See who has access to workbooks

list_all_users

View all users with roles and details

list_all_groups

View all groups with member counts

get_user_permissions

Get detailed user permissions

list_projects_permissions

Audit project permissions

get_site_info

Get site statistics and quotas

audit_workbook_usage

Comprehensive workbook audits

list_user_groups

See user group memberships