Provider REST API
ProductivityConnect Claude to Jotform
Read Jotform forms and submissions, and manage submissions, form copies and webhooks. Toolspoke puts 17 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.
- Connection
- Provider REST API
- Authentication
- API key
- Actions exposed
- 17
- What a call bills
- Nothing
- Adapter
- Maintained by Toolspoke
Connected in three steps
- 1
Install Jotform
Open the marketplace in your workspace, add Jotform to the project your agents work in, and it appears on the gateway immediately.
- 2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
- 3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.
.mcp.json{
"mcpServers": {
"toolspoke": {
"type": "http",
"url": "https://toolspoke.com/mcp"
}
}
}One block covers every tool you have installed. Jotform shows up in the client as soon as your policy allows it, and so does everything else you install later.
Where the address goes, per client
- Claude Code
Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp- Claude and Claude Desktop
Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp- Cursor
~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }- Codex
~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"- VS Code
.vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }
What Jotform asks for
API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.
- API keyRequired
- Jotform → My Account → API (jotform.com/myaccount/api) → Create New Key. Set its permission to Full Access for the write operations; Read Access covers every read.
- 32 hex characters
- API hostOptional
- Leave blank for a standard account. Use https://eu-api.jotform.com for an EU account, or https://hipaa-api.jotform.com for a HIPAA account.
- https://eu-api.jotform.com
What Claude can do in Jotform
17 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.
- Reads
- 10Reads
- Writes
- 2Writes
- Destructive
- 5Destructive
Reads
10Fetches data and changes nothing.
get_userRead the account the key belongs to, including its plan and limits.
get_usageRead this month's usage against the plan's limits, such as submissions, uploads and payments.
list_formsList your forms with their status, URL and submission counts. filter is an object such as {"status":"ENABLED"} or {"title:matches":"Survey"}. Proves the key reads real data, which is why an install tests itself with it.
get_formRead one form's basic information. The form id is the number in its URL (form.jotform.com/<formId>).
list_questionsList a form's questions, keyed by question id. Those ids are the keys of a submission's answers and of create_submission's submission object.
list_form_submissionsList a form's submissions with every answer. filter is an object such as {"created_at:gt":"2026-10-01 00:00:00"}. Answers are what respondents typed, so the response is not written to the audit log.
list_submissionsList submissions across all your forms, newest first. Not written to the audit log.
get_submissionRead one submission with every answer. Not written to the audit log.
list_form_reportsList the reports built on a form, with their URLs.
list_webhooksList the webhook URLs a form posts its submissions to, keyed by webhook id.
Writes
2Creates or updates something on the other side.
edit_submissionChange answers on an existing submission. submission maps question ids to the new answers; questions left out keep their answers.
clone_formMake a copy of a form in your account. Returns the new form.
Destructive
5Deletes or permanently alters something. Worth granting on purpose.
create_submissionSubmit a response to a form, as if a respondent had filled it in. submission maps question ids to answers, e.g. {"3":"Ada","4":{"first":"Ada","last":"Lovelace"}}. Destructive because it runs the form's side effects: notification and autoresponder emails, integrations and webhooks.
delete_submissionDelete one submission. A respondent's answers cannot be recovered afterwards.
delete_formDelete a form. Its link stops working for respondents at once.
create_webhookSend a form's submissions to a URL. Destructive because from then on every respondent's answers leave Jotform for that address, which may be outside your organization.
delete_webhookDelete a form's webhook. Whatever relied on it stops receiving submissions.
What it will not do
Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.
- It cannot call anything else
- The 17 actions above are the whole of it. A call to any other name is refused before it reaches Jotform rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
- It reaches no further than your credential
- Toolspoke holds no access to Jotform of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
- It never hears from Jotform
- Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Jotform. An agent has to ask.
- It does not smooth over provider limits
- Toolspoke does not retry, queue or back off around Jotform's own rate limits. A call that Jotform refuses comes back to the agent as a failed call.
Before you connect it
What can Claude do in Jotform?
17 named actions: 10 that only read, 2 that write and 5 that delete or permanently alter something. They include get_user, get_usage and list_forms. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.
What credentials does the Jotform connector need?
API key. The connector asks for api key, and optionally api host. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.
Does the Jotform connector work with Cursor and Codex, or only Claude?
Any client that speaks MCP, and every one of them gets the same 17 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.
What does the Jotform connector not do?
The 17 actions above are the whole of it. A call to any other name is refused before it reaches Jotform rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Jotform of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Jotform. An agent has to ask. Toolspoke does not retry, queue or back off around Jotform's own rate limits. A call that Jotform refuses comes back to the agent as a failed call.
Can I limit which actions an agent can call?
Yes, in two places. The project switches Jotform's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.
What gets recorded when an agent calls Jotform?
Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.