Manage HelpCrunch chats, customers, agents and knowledge-base articles. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"helpcrunch": {
"url": "https://helpcrunch.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"helpcrunch": {
"type": "http",
"url": "https://helpcrunch.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your HelpCrunch API key.
Create one in HelpCrunch → Settings → API. Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your HelpCrunch API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the HelpCrunch connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
helpcrunch_list_customers | read | List customers List / search customers (people who chatted in). Optionally filter with a single field/operator/value clause (comparison AND), sort (e.g. customers.firstSeen, customers.lastSeen) with order, and paginate with limit/offset. HelpCrunch REST: POST /customers/search. |
helpcrunch_get_customer | read | Get customer Get a single customer by id. HelpCrunch REST: GET /customers/{id}. |
helpcrunch_list_chats | read | List chats List / search chats (conversations). Optionally filter with a single field/operator/value clause (comparison AND), sort (e.g. chats.createdAt) with order, and paginate with limit/offset. HelpCrunch REST: POST /chats/search. |
helpcrunch_get_chat | read | Get chat Get a single chat (conversation) by id. HelpCrunch REST: GET /chats/{id}. |
helpcrunch_get_chat_messages | read | Get chat messages Get the messages of a chat (conversation), newest first (sorted by createdAt DESC). Paginate with limit (max 100) / offset. HelpCrunch REST: GET /chats/{id}/messages. |
helpcrunch_list_agents | read | List agents List agents (support staff / operators) in the account, with role and email. Paginate with limit/offset. HelpCrunch REST: GET /agents. |
helpcrunch_list_departments | read | List departments List departments (groups of agents that chats can be routed to), each with its agents. Paginate with limit/offset. HelpCrunch REST: GET /departments. |
helpcrunch_list_applications | read | List applications List applications configured in the account — web chat widgets, iOS/Android apps, and social integrations (id, name, displayName, active, type). HelpCrunch REST: GET /applications. |
helpcrunch_get_organization | read | Get organization Get the organization's live-chat availability status — domain, whether the team is online (teamOnline), and whether chat is enabled (chatEnabled). HelpCrunch REST: GET /organization. |
helpcrunch_create_message | write | Create message POSTS a message into a LIVE chat — a customer-visible reply (type "message") or an internal private note (type "private"). Set `agent` (agent id) for agent messages; omit it for customer messages. HelpCrunch REST: POST /messages. |
helpcrunch_update_chat_status | write | Update chat status CHANGES the status of a LIVE chat (e.g. mark it opened, pending, on hold, or closed). HelpCrunch REST: PUT /chats/status. |
helpcrunch_assign_chat | write | Assign chat ASSIGNS (or unassigns) a LIVE chat to an agent. Pass `assignee` (agent id) to assign; omit it (or pass null) to unassign. HelpCrunch REST: PUT /chats/assignee. |
helpcrunch_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
helpcrunch_request_feature | Request a missing feature Tell usefulapi that the user needs something the HelpCrunch tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
helpcrunch_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED HelpCrunch tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
helpcrunch_cancel_subscription | Cancel the Pro subscription Cancel the caller's HelpCrunch Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run helpcrunch_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
Pro covers this HelpCrunch server only. Subscribe with helpcrunch_upgrade (it returns a Stripe Checkout link). Cancel any time with helpcrunch_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running helpcrunch_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by HelpCrunch. The server calls the HelpCrunch API with your own HelpCrunch access, so it sees only the data that your account can see.
The login page asks for your HelpCrunch API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your HelpCrunch API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the HelpCrunch API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in HelpCrunch.
Yes, if you approve it. 3 of the 12 HelpCrunch tools can create or change data. The other 9 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this HelpCrunch server only. Run helpcrunch_usage_status to see how many calls you used.
Ask the AI to run helpcrunch_upgrade: it returns a Stripe Checkout link. To cancel, run helpcrunch_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with helpcrunch_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.