What is an MCP?

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools securely. In short: it gives your AI assistant the ability to interact with apps on your behalf.

Tally's MCP server uses this standard to give your AI assistant direct access to your Tally workspace and forms. Once connected, your assistant can:

• Create forms from a plain-language description
• Edit existing forms: add, remove, or update fields and settings
• Browse your workspace: list forms, search by name and organize
• Fetch submission data: to then analyze, visualize, and summarize it right inside the conversation

How to set it up

Connect any MCP-compatible AI assistant to Tally using this server URL:

https://api.tally.so/mcp

For detailed setup instructions per assistant (Claude, Claude Code, ChatGPT, Cursor, and others), see the Tally MCP Developer Docs.

What you can do

Create forms from a description

Describe the form you need and your AI assistant builds it in Tally.

• "Create a client intake form with fields for company name, project scope, budget range, timeline, and a file upload for their brief."
• "Build a post-event feedback survey with a 0–10 rating, a dropdown for session name, and a long text field for comments."
• "Make a registration form for a workshop."

Edit existing forms

Make changes to live forms without opening the Tally editor.

• "Add a required phone number field to my contact form."
• "Remove the company size question from the partner application form."
• "Make the email field required on my waitlist form."

Browse and organize

Navigate your workspace and manage forms through conversation.

• "Show me all forms I updated in the last week."
• "List my published forms."

Fetch and analyze submission data

This is where Tally's MCP integration becomes much more than a form management shortcut. Your AI assistant doesn't just retrieve submissions, it can work with the data in ways that go far beyond what a built-in dashboard offers.

Visualize your data

• "Pull all submissions from my customer feedback form and create a bar chart showing the distribution of satisfaction ratings."
• "Show me a trend line of weekly signups from my waitlist form over the past 3 months."
• "Create a pie chart of the most selected options in the 'How did you hear about us?' question."

Run sentiment analysis on open-ended responses

• "Analyze the tone of responses to the 'Any additional feedback?' field on my product survey. Group them into positive, neutral, and negative."
• "Summarize the key themes across all long-text answers in my onboarding feedback form."

Calculate scores and metrics

• "Calculate the NPS score from my latest customer satisfaction survey."
• "What's the average rating on my post-workshop feedback form, broken down by session?"
• "Compare the completion rate between my two onboarding forms."

Qualitative analysis at scale

• "Read through all 200 responses to 'What would you improve?' and give me the top 5 recurring suggestions with example quotes."
• "Group the open-ended feedback from my beta testing form into feature requests, bug reports, and general praise."
• "Which responses mention pricing concerns? Summarize what they're saying."