Tally

MCP server for Tally.so - manage forms through AI with natural language commands and safety-first bulk operations
  • html

7

GitHub Stars

html

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can run and use the Tally MCP Server to let your AI assistants manage Tally forms and data without switching between tools. It supports natural language form creation and management, secure authentication, and real-time insights, making it easier to build, modify, and analyze forms inside your AI workflows.

How to use

Describe what you want in natural language and let the MCP server translate that into actions like creating forms, updating settings, exporting submissions, or sharing forms. You can run operations across multiple forms and workspaces with safety features that require preview and confirmation before executing bulk changes. You can also access analytics, manage teams, and export data from your AI session.

How to install

Prerequisites: you need Node.js and npm installed on your system.

Install dependencies and run the development or deployment flow as described below.

# Install dependencies
npm install

# Development server (if you want to run locally for testing)
npm run dev

# Build for deployment to Cloudflare Workers (if you are building the worker)
npm run build:worker
npx wrangler deploy

Configuring clients to connect

You have multiple options to connect an MCP client to the server. Choose the approach that matches your workflow and client capabilities.

Option A: Claude Desktop with mcp-remote (recommended for Claude users) uses a remote MCP URL and an authorization header.

{
  "mcpServers": {
    "tally-remote": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://tally-mcp.focuslab.workers.dev/mcp",
        "--header",
        "Authorization: Bearer YOUR_AUTH_TOKEN"
      ]
    }
  }
}

Option B: Direct HTTP integration (for clients that support custom headers)

Connect directly via an HTTP-based MCP URL with the authorization header.

{
  "mcpServers": {
    "tally": {
      "url": "https://tally-mcp.focuslab.workers.dev/mcp",
      "transport": "http-stream",
      "headers": {
        "Authorization": "Bearer YOUR_AUTH_TOKEN"
      }
    }
  }
}

Option C: Local proxy for custom setups

If you prefer a local proxy, you can run it and point your client to the local URL.

# Start the local proxy
npm run proxy

# Claude configuration example
# Server URL: http://localhost:3001/mcp
# Transport: http-stream
# Authentication: None

Available tools

create_form

Create new Tally forms with custom fields based on your natural language description.

modify_form

Update existing form configurations, such as changing fields, layout, or options.

get_form

Retrieve detailed information about a specific form, including fields and settings.

list_forms

List all forms within your account or workspace for quick browsing.

delete_form

Remove forms you no longer need from your account.

get_submissions

Access form submission data for analysis or export.

analyze_submissions

Get insights from form responses, such as completion rates and patterns.

share_form

Generate sharing links and embed codes to publish forms.

manage_workspace

Handle workspace-level settings and configurations.

manage_team

Manage team members and their permissions.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational