Smartsheet MCP Server now connects AI agents to Amazon Quick and Kiro

What the Smartsheet MCP Server offers

According to the AWS post, the Smartsheet MCP Server gives AI assistants a standardized protocol for working with Smartsheet data. It spans more than 40 tools for exploring, creating and managing sheets, rows, columns and automations. Users can update task statuses, create rows and modify project structure through natural language.

AWS says the server delivers precisely structured context, including row relationships, column types, cell history and comments. This produces token-efficient payload sizes rather than returning raw API payloads. According to the post, that choice reduces cost and improves latency at scale, for example when running hundreds of AI-assisted queries across a project portfolio.

The server is available at three regional endpoints: Commercial US, EU and AU. It uses Streamable HTTP transport (MCP spec versions 2025-06-18 and 2025-03-26) and authenticates with either OAuth 2.0 or a Personal Access Token.

Two paths: Amazon Quick and Kiro

Amazon Quick is described as an agentic AI workspace for business users, project managers and operations teams, who can ask questions, update sheets and build dashboards without writing code. Kiro is an agentic IDE where developers connect to Smartsheet through MCP to reference project specs, update task status and track dependencies without leaving their coding workflow.

The post uses a software team tracking a sprint in Smartsheet as an example. A project manager can ask Amazon Quick which sprint tasks are blocked this week. The chat agent queries the MCP server, pulls the relevant rows and returns a summary with owner names and due dates, generated from live data without a report or dashboard. A developer can ask Kiro to show open backend tasks assigned to them. When the fix is committed, a Kiro hook automatically sets the matching row status to Complete.

AWS suggests choosing Amazon Quick for a fully managed, organization-wide solution with pre-built OAuth and no app registration on the user side. Kiro is positioned as the lightweight option for individual developers, needing only a config file and a personal access token.

Requirements and setup

Before connecting, users need the following:

• An active AWS account with suitable IAM permissions for the service being connected
• A Smartsheet account on a Business, Enterprise or AWM plan
• A Smartsheet Personal Access Token, or OAuth credentials if the client supports them
• For Amazon Quick: Author or higher permissions
• For Kiro: the IDE installed from kiro.dev with Node.js available

In Amazon Quick, Smartsheet appears as a pre-built connector in the Connectors directory. Admins select the tile, enter a name, the base URL, the client ID and secret from a Smartsheet Developer Tools app registration, plus token and auth URLs. They then review tools and permissions and choose who can access the connection on the Publish page. Afterward, the chat agent can handle prompts such as "What projects in our portfolio are currently At Risk?"

For Kiro, setup takes a single JSON block added to the MCP configuration, such as .kiro/settings/mcp.json for workspace scope. The example uses a Personal Access Token, while AWS recommends OAuth for production deployments. Once Kiro starts, the Smartsheet tools are available across chat, spec planning and hooks-based automation.

What it means for teams

The release lets teams that already manage work in Smartsheet bring that data into AI tools without switching applications. Business users get a managed connector in Amazon Quick, while developers can keep project context next to their code in Kiro. Both routes use the same Smartsheet toolset, so the choice depends on where the work happens, according to AWS.