Jotform MCP server for your AI

In your Jotform account, go to Account → API → Create New Key, then paste the value into the API key field on the connect form. There is no OAuth popup and no re-authentication step. The key acts as your one Jotform account, so the agent reaches that account's forms, questions, submissions, form properties, reports, folders, webhooks, uploaded files, and account info — nothing outside it.

Yes. The connect form has an optional Data region field that accepts us, eu, or hipaa. Set it to match where your account is hosted so calls go to the right Jotform API. Standard accounts can leave it blank.

Jotform identifies every field by a question id (qid), and submission answers are keyed by that qid rather than by label. get_submission returns the question text and type alongside each answer, so single-submission lookups read fine on their own. For list-level pulls with get_form_submissions or list_submissions, have the agent run get_form_questions first so it can map each qid to its label before summarizing.

It can build and change them. create_form, create_forms, and clone_form produce new forms; create_form_question, create_form_questions, update_form_question, and delete_form_question shape the fields; set_form_properties updates title, status (ENABLED/DISABLED), thank-you behavior, styling, and expiration. All of that is write access, so it needs full access: a paid plan, and not a read-only teammate.

get_usage reports this month's submissions received, SSL submissions, API requests, upload space used, and payment submissions against your remaining limits, and get_user returns the account type and plan alongside its usage limits. There is also a Plan limit approaching trigger that fires when monthly submissions, uploads, or views get close to the plan ceiling. Useful if a form is running a campaign and you would rather not find out at the cap.

delete_submission removes a submission permanently as soon as the AI calls it, so it is the one to be most careful with. delete_form is gentler: it moves the form to the trash, and it can be restored from the Jotform UI. delete_form_question, delete_folder, delete_report, and delete_form_webhook (which removes a webhook by its index) round out the destructive set. Read-only access, on the Free plan or for a teammate, blocks all of them.

No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.

Any client that supports a remote Streamable HTTP MCP server: Claude Desktop, Claude Web, Claude Code, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.

Connect Jotform in PopMCP first, then run claude mcp add --transport http popmcp https://app.popmcp.com/mcp in a terminal. Inside Claude Code, run /mcp and sign in to PopMCP in the browser window it opens, ticking Jotform on the consent screen. The Jotform tools are then available in that session, and no Jotform credential is stored on your machine.

Loading 44 tool definitions into every conversation burns context before the work starts. PopMCP loads a curated 23-tool set covering the everyday workflows and keeps the rest searchable, so your AI pulls a specialist tool only when a task needs it. Every tool stays searchable, and on Scale the owner can load the full catalog for a teammate's connection.

A tool is something your AI calls, and there are 44 here. A trigger is something PopMCP watches for you: 13 Jotform events that can start work on the PopMCP side. Triggers never enter your AI client's context, and none of them ask you to paste a callback URL into Jotform.