MCP server

Chatform runs a Model Context Protocol server at:

https://api.chatform.in/mcp

Paste that link into an AI app and sign in, and it can list your forms, read responses, analyse completion rates, author a new form from a description, publish it, and reach the rest of the API when it needs something the named tools do not cover.

It is the same worker, the same keys and the same scopes as /v1. Nothing here can do anything a key could not already do over HTTP, with one deliberate subtraction: nothing can delete.

Connect with one link

Most apps need nothing but the URL. They open your browser on a Chatform page that asks Allow Claude to use Chatform? (or Cursor, or ChatGPT), you click Allow, and the app keeps itself signed in from then on. No key to create or paste. The same steps, with copy buttons, are in every form's Integrate tab under AI assistants.

Connecting an organization is an owner or admin decision, the same as creating an API key. Each connection appears under Connected in the AI assistants panel, where Disconnect cuts it off at once.

Use an API key instead

For a server, a script, or a client that cannot open a browser, send a secret key on every request instead. Keys need a plan with API access.

Get a key

MCP needs more than a new key is given by default. A default secret key can read forms and responses; it cannot publish, read analytics or export, so an assistant using one fails with insufficient_scope on the first interesting request.

In Settings → API keys, create a secret key with these scopes:

ai:generate is deliberately not in that list. It is the one scope that spends money — a generation bills your plan's AI allowance — and an assistant can author a form for free by reading list_blocks and calling create_form. Add it only if you specifically want Chatform's own designer model available to the agent.

GET /api/keys/scopes returns this set as the agent preset if you are building your own key UI.

Install with a key

claude mcp add --transport http chatform https://api.chatform.in/mcp \
  --header "Authorization: Bearer $CHATFORM_SECRET_KEY"

The tools

Thirty, which is a budget rather than an accident: clients cap how many tools they will load — Cursor at forty — and that ceiling is shared with every other server you have connected.

Getting oriented

Forms

Responses

Webhooks

Everything else

Four tools reach the whole developer API without putting forty more schemas in front of the model:

They are bounded by the spec: only the operations published at https://api.chatform.in/openapi.json are reachable. The dashboard's own /api/* routes and the respondent /p/* channel are not part of that document and cannot be called with a key, so an assistant cannot reach them however it asks.

Two areas are reachable only this way, on purpose:

• Driving a live conversation — opening a chat session and exchanging messages turn by turn, plus session uploads. Fifteen operations, and a niche job for an assistant: submit_response records answers directly without pretending to be a respondent. If you want named tools for testing a form conversationally, that is a reasonable ask.
• Incremental response building — recording answers one at a time, then completing or abandoning GET /v1/responses/{id}/next and its siblings. submit_response does the one-shot version, which is what an import or an agent filling a form actually needs.

Building a form

There is no "generate a form" tool, and that is on purpose — your assistant is already the model. It reads list_blocks for the question-type contract, writes the document itself, and calls create_form. Chatform spends nothing on inference, and you are not paying twice for the same sentence.

Build me a 5-question customer onboarding form, publish it, and show me the completion rate once people start answering.

That runs list_blocks → create_form → publish_form → get_form_analytics.

When editing an existing form, the assistant must read the document first: update_form replaces the whole draft, so a partial document silently removes every question missing from it. For a setting ("make it navy", "close it after 200 responses", "sound more professional") use update_form_settings instead: it changes those keys and nothing else, refuses a value that does not fit with the reason, and reports a setting your plan does not include without applying it.

What is not here

• Deletes. No tool deletes a form, a response, an answer or a webhook, and chatform_api_write refuses the DELETE method outright — whatever scopes the key holds. Respondent free text is attacker-controlled input, and an assistant reading it should not be one confused tool call away from destroying data. Delete from the dashboard.
• Key and plan management. No key can mint keys or change a plan; see Scopes.
• .xlsx. The API exports csv and json; the typed workbook is dashboard-only. See Spreadsheets.
• Deleting responses in bulk, sending a synthetic webhook test, and moving a form between workspaces. Each has a dashboard route and no API one yet — tracked in tooling/check-spec-coverage.ts, which now fails the build if a new dashboard capability appears without either a /v1 equivalent or a written reason.

Plan and usage

An app connected with one link works on every plan. On a plan with API access each tool call that reaches an endpoint counts as one API request; on Free, connected apps share an allowance of 1,000 calls a month. A pasted key needs a plan that includes API access. Listing the tools is free, which is why an assistant can connect and show you what it could do before the plan refuses the first call — and the refusal says which plan lifts it.

Per-question analytics needs a plan with advanced analytics. Below that, get_form_analytics returns the headline numbers and says which sections the plan withheld, so an assistant will not report an empty funnel as "no data".

Things to know

• search_responses is a substring match, not semantic search, and results are not ranked. Searching unhappy will not find dissatisfied. To find themes, page through list_responses with answers included and read them.
• Results are paginated small — ten rows by default — and long answers are truncated with a truncated flag rather than silently cut.
• Exports come back inline. export_responses returns an id; once it is ready, check_export returns the CSV or JSON Lines itself, up to 200 KB per call, with a next_offset to read on. An assistant whose sandbox blocks api.chatform.in never needs the download link.
• Keys pinned to specific forms still are. A restricted key sees 404 for anything outside its list, through MCP as over HTTP.

Troubleshooting

Every error carries a request_id. Quote it if you contact support.