Tally Forms MCP Server

Created By
Ward boone2 months ago
Tally integrates with AI assistants like Claude, ChatGPT, and Cursor through the Model Context Protocol (MCP). This lets you create forms, edit them, and pull submission data into your AI assistant for analysis, visualization, and insights that go far beyond what any form builder dashboard can do. No code needed. No switching between tabs. Just describe what you want in plain language.
Overview

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."
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Ward boone
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

8 hours ago