Forecast MCP Server

The Forecast MCP server connects your Forecast data to AI assistants. It gives an assistant a set of functions for reading and acting on your projects, people and time, so instead of clicking through Forecast yourself, you can just ask.

Jump to...

• What is MCP?
• What it does 
• Built-in safeguards
• Get started 

What is MCP?

Model Context Protocol (MCP) is an open standard that enables AI models to securely connect to external tools, databases, and data sources. By providing a standardized way for these systems to communicate, MCP allows AI assistants to access and use real-time information dynamically.

There are two ways to use the Forecast MCP Server: 

• Through Ask AI, built into Forecast 

• By connecting your preferred AI assistant. Setup instructions can be found in the Forecast AI: Getting Started help guide.

What it does

Ask questions about your work in plain language. Get insights into project and portfolio health, team capacity, time and billing, leave conflicts, and more.

Try asking:

• "How's the (Project Name) project tracking?" 

• "Who's over-allocated next month?"

Take action using natural language. Reassign work, move tasks through your workflow, reschedule tasks or project phases, and log time.

Try this command: 

• "Reassign all open tasks on the (Project Name) project from (Team Member Name) to (Team Member Name)" 

To explore everything you can ask, the actions you can take, example prompts, and available tools, see: Forecast AI: Capabilities and Prompt Examples   

Built-in safeguards

Every change is previewed first, and nothing is applied until you confirm it:

• The assistant shows you exactly what it's about to change and waits for your go-ahead.
• In a batch, you can deselect any rows you don't want touched and confirm the rest.

• You'll get a warning if a change would push work past a project's end date, or if a rescheduled allocation would clash with another.

For more details on safeguards, see: Forecast AI: Getting Started 

Get Started

• Forecast AI: Getting Started — Get started with Ask AI directly within Forecast, or connect your preferred AI assistant (such as Claude or ChatGPT) and make your first request. You can also learn more about the safeguards in place.
• Forecast AI: Capabilities and Prompt Examples — Explore the full list of questions you can ask and actions you can take, with example prompts.
• How Forecast's AI Features Use Your Data — This article explains how Forecast's AI features use your data.