Read Helpwise conversations, contacts, tags and reports; note, tag, assign, close; send one email. 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": {
"helpwise": {
"url": "https://helpwise.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"helpwise": {
"type": "http",
"url": "https://helpwise.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 Helpwise API key and Helpwise API secret.
Find both in Helpwise under Settings → Integrations → API (the API needs a plan that includes API access, Premium and up). Your key and secret are used only to call the Helpwise API on your behalf; they are 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 Helpwise API key and Helpwise API secret. 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.
| Tool | Type | What it does |
|---|---|---|
helpwise_list_conversations | read | List conversations List conversations (threads) of one or more inboxes, newest first, with subject, snippet, tags, assignee, read/starred/closed flags and contact. Pick the folder with `folder` (default: all). Page with `next_page_token`. Inbox ids come from helpwise_list_inboxes. GET /conversations. |
helpwise_get_conversation | read | Get conversation One conversation with its messages, notes, drafts, assignment and contacts. Page long conversations with `page_token` from the previous reply. GET /inboxes/{inbox_id}/conversations/{conversation_id}. |
helpwise_list_contacts | read | List contacts List contacts (name, company, job title, emails, phones, id). Page with limit and offset. GET /contacts. |
helpwise_search_contacts | read | Search contacts Search contacts by a name, email or phone term. Page with limit and offset. GET /contacts/search. |
helpwise_get_contact | read | Get contact One contact with emails, phones, company, custom fields and recent conversations. GET /contacts/{id}. |
helpwise_list_tags | read | List tags All tags (id, name, colour, parent, inbox). Use the ids with helpwise_apply_tags. GET /tags. |
helpwise_get_tag | read | Get tag One tag by id. GET /tags/{id}. |
helpwise_get_report | read | Overall report Overall and team-performance report for a date range: new/closed/assigned conversations (with change vs the previous period), inbound/outbound messages per day, busiest hour/day, average first response, response and resolution time, CSAT and per-agent performance. Optional inbox and tag filters. GET /reports. |
helpwise_get_tags_report | read | Tags report Per-tag report for one inbox and a date range: conversations per tag (and share), open conversations, average response, first-response and resolution time. GET /inboxes/{inbox_id}/reports/tags. |
helpwise_list_inboxes | read | List inboxes List the account's inboxes (mailboxes) with id, name, address and type. Use the ids in the other tools. POST /mailboxes/list (V0). |
helpwise_list_users | read | List users List the team members (agents) with access to an inbox: id, name, email. Use the ids with helpwise_assign_conversation. POST /users/list (V0). |
helpwise_get_current_user | read | Get current user The Helpwise user the API key belongs to (name, email, id). POST /users/me (V0). |
helpwise_create_contact | write | Create contact WRITE: create a new contact in Helpwise (name, company, job title, emails, phones, custom fields). Nothing is sent to the person. Creating the same email twice may create a duplicate. POST /contacts. |
helpwise_update_contact | write | Update contact WRITE: change a contact's name, company, job title, emails, phones or custom fields. Helpwise updates with PUT, so this tool first reads the contact and sends the current values together with your changes; a list you pass (emails, phones, custom_fields) REPLACES the old list. Nothing is sent to the person. PUT /contacts/{id}. |
helpwise_add_note | write | Add note WRITE: add an internal note to a conversation. Visible to your Helpwise team only; it is not sent to the customer. Notes cannot be deleted through this API. POST /notes/add (V0). |
helpwise_assign_conversation | write | Assign conversation WRITE: assign a conversation to a team member (user id from helpwise_list_users), or pass assigned_to 0 to unassign it. The assignee may be notified by Helpwise. POST /threads/assign (V0). |
helpwise_close_conversations | write | Close conversations WRITE: close up to 25 conversations (mark them done). They can be reopened with helpwise_reopen_conversations. Nothing is sent to customers. PUT /conversations/action/close. |
helpwise_reopen_conversations | write | Reopen conversations WRITE: move up to 25 conversations back to the inbox (reopen closed ones). Nothing is sent to customers. PUT /conversations/action/moveToInbox. |
helpwise_apply_tags | write | Apply tags WRITE: apply existing tags (ids from helpwise_list_tags) to up to 25 conversations. Tags can drive Helpwise automations. Applying a tag already present changes nothing. POST /tags/apply. |
helpwise_remove_tags | write | Remove tags from conversations WRITE: take tags off up to 25 conversations. The tags themselves are not deleted. POST /tags/remove. |
helpwise_send_email | write | Send email WRITE: SEND A REAL EMAIL from a Helpwise inbox to the given customer address(es). Irreversible; once sent it cannot be recalled. At most 10 recipients in total (to + cc), one message per call; never use it for lists or campaigns. This starts a new message (it is not a reply on an existing conversation). The body is plain text (blank line = new paragraph); it is sent as HTML. POST /emails/send_mail (V0). |
helpwise_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. | |
helpwise_request_feature | Request a missing feature Tell usefulapi that the user needs something the Helpwise 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. | |
helpwise_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Helpwise 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. | |
helpwise_cancel_subscription | Cancel the Pro subscription Cancel the caller's Helpwise 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 helpwise_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 |
| Proper user | $9/mo · $90/yr | Unlimited |
Pro covers this Helpwise server only. Subscribe with helpwise_upgrade (it returns a Stripe Checkout link). Cancel any time with helpwise_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running helpwise_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 Helpwise. The server calls the Helpwise API with your own Helpwise access, so it sees only the data that your account can see.
The login page asks for your Helpwise API key and Helpwise API secret. See Before you connect for where to find them.
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 Helpwise API key and Helpwise API secret. 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 Helpwise 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 Helpwise.
Yes, if you approve it. 9 of the 21 Helpwise tools can create or change data. The other 12 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 Helpwise server only. Run helpwise_usage_status to see how many calls you used.
Ask the AI to run helpwise_upgrade: it returns a Stripe Checkout link. To cancel, run helpwise_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 helpwise_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.