smartsheet
MCP server providing healthcare analytics capabilities for Smartsheet, including clinical note summarization, patient feedback analysis, and research impact assessment
claude mcp add --transport stdio terilios-smartsheet-server node server.js \ --env MCP_LOG_LEVEL="info" \ --env AZURE_OPENAI_KEY="<your-azure-openai-key>" \ --env SMARTSHEET_BASE_URL="https://api.smartsheet.com/2.0" \ --env SMARTSHEET_API_TOKEN="your-smartsheet-api-token" \ --env AZURE_OPENAI_ENDPOINT="https://<your-endpoint>.openai.azure.com/"
How to use
The Smartsheet MCP Server exposes a comprehensive set of tools to automate and manage Smartsheet workbooks, sheets, and data through the MCP protocol. It includes capabilities for retrieving column metadata and sample data, writing new rows with intelligent handling of system columns and formulas, updating and deleting rows, and performing advanced searches across sheets. The server also provides powerful column management tools (add, delete, rename) and batch analysis features designed for healthcare analytics, enabling AI-driven scoring and reporting. Use these tools to integrate Smartsheet into automated workflows, ensure data integrity, and enable scalable, formula-aware data operations.
To interact with the server, call the available MCP tools through the standard MCP interface. Key capabilities include:
- get_column_map / get_sheet_info for inspecting sheet structure and sample data
- smartsheet_write for appending new data with duplicate detection and formula awareness
- smartsheet_update and smartsheet_delete for modifying or removing rows with validation
- smartsheet_search for complex, column-aware search across sheets
- Column management tools (smartsheet_add_column, smartsheet_delete_column, smartsheet_rename_column) for dynamic schema changes
- get_all_row_ids and start_batch_analysis for batch processing and AI-driven analytics
- get_job_status and cancel_batch_analysis for monitoring long-running analyses These tools enable AI agents to programmatically manage Smartsheet data, enforce business rules, and generate structured outputs suitable for downstream automation.
How to install
Prerequisites:
- Node.js v16/18/20 installed
- npm installed
- Access token for Smartsheet API and any required Azure OpenAI keys if you plan to use batch analysis features
Step 1: Clone the repository
git clone https://github.com/terilios/smartsheet-server.git
cd smartsheet-server
Step 2: Install dependencies
npm install
Step 3: Configure environment Create a .env file or set environment variables as shown in the mcp_config:
SMARTSHEET_API_TOKEN=your-smartsheet-api-token
SMARTSHEET_BASE_URL=https://api.smartsheet.com/2.0
AZURE_OPENAI_ENDPOINT=https://<your-endpoint>.openai.azure.com/
AZURE_OPENAI_KEY=<your-azure-openai-key>
Step 4: Run the MCP server
# Depending on your setup, the server might be started via npm scripts or directly
node server.js
Step 5: Verify the server is running
- Check logs for startup messages
- Send a test MCP request to ensure endpoints respond as expected
Additional notes
Notes and tips:
- Ensure your Smartsheet API token has the necessary permissions for the sheets you intend to manipulate.
- If using batch analysis with Azure OpenAI, configure your endpoint and key securely and be mindful of token usage limits.
- The server supports environment-based configurations; consider using a process manager (e.g., PM2) for production deployments.
- For large sheets, prefer get_all_row_ids before bulk operations to manage pagination and performance.
- When adding or renaming columns, be aware of existing formulas that may reference columns by name or ID; the server attempts to update references automatically but validate critical sheets after structural changes.
Related MCP Servers
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
mcp-yfinance
Real-time stock API with Python, MCP server example, yfinance stock analysis dashboard
mcp-aoai-web-browsing
A minimal Model Context Protocol 🖥️ server/client🧑💻with Azure OpenAI and 🌐 web browser control via Playwright.
cloudwatch-logs
MCP server from serkanh/cloudwatch-logs-mcp
servicenow-api
ServiceNow MCP Server and API Wrapper
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools