Hellohop

hellohop-mcp

[M8ven Verified]

HelloHop is an independent WhatsApp API for developers: send and receive messages, automate groups and communities, and get signed webhooks, from $25 USD per number per month with a free sandbox.

This is the HelloHop MCP server. It lets an MCP client (for example Claude Desktop, Claude Code or Cursor) work with one channel of the public API: read the channel's status, the chats it has observed, recent messages, its groups and communities, and a contact. Sending (a text, media by URL, a poll, a reaction) is off by default and available only when you turn it on. Docs: https://hellohop.app/docs/mcp. HelloHop is not affiliated with or endorsed by WhatsApp or Meta.

Install

Requires Node.js 22 or later. Run it with npx, no separate install step:

npx -y hellohop-mcp

Your MCP client starts the server for you once it is configured (see Claude Desktop and Claude Code below). The server reads its settings from the environment variables listed under Environment.

Tools

check_numbers (always registered; it sends no message) starts a number check from 1 to 50 numbers (POST {base}/sessions/{channel}/number-checks, plus refresh if given), or reads one by job_id (GET the check, then a page of its rows with offset, limit and status). The check runs in the background on the channel's own connected non-sandbox number, spaced out, with a daily check allowance by number age, so a long list takes hours or days and it cannot be made faster. The number checker is included with every paid number. The account needs at least one active non-sandbox channel, including one covered by a paid, complimentary, promotional or admin grant. Otherwise the service returns 403 number_checker_requires_paid_number; a sandbox request from an eligible account returns 403 number_checker_requires_non_sandbox_channel. A paused check says why and resumes by itself (only channel_down waits for you; account_suspended must be resolved); a failed check reports its code and reason in failure (check_failed for an upstream failure). Read its reason before retrying. Rows carry phone_e164, country, jid, lid, is_business (present only when true), verified_name, checked_at, and cached with age_seconds. A check is a point-in-time answer and can be wrong or out of date; it does not promise delivery.

Not exposed, on purpose: group and community invite links (an agent could paste an open invite into a chat), media download (bytes, not JSON) and webhook configuration.

get_group returns the group's participant list, which is your own group data, so it enters the MCP client's context like any other tool result. Use it only with a client you trust with those member identities.

The public API forwards only limit (1 to 500) and before on the conversation read, so read_messages pages with those two and no other query string reaches the API. The other list tools take no paging parameters.

A chat is sent in the URL path without percent-encoding, because the API refuses any path containing %. A chat containing anything other than letters, digits and @ . : _ + - is refused before a request is made.

Every request sends Authorization: Bearer <token>. A successful response is returned as JSON text. An HTTP error is returned as a tool error with status, code and error, plus retry_after (and window, resets_at, ambiguous, id) when the API sends them. The token is redacted from every string returned, success bodies included. Nothing is retried automatically, and a redirect is refused rather than followed.

Environment

Required before tool use, not installation: the server can start without a token or channel ID.

An account key starts with hh_acct_ and works in GATEWAY_API_TOKEN without any other change. GATEWAY_CHANNEL_ID still selects one owned number per server. Create the key in Account in the console; it is shown once. Rotate with Regenerate, then update this configuration. The key cannot manage billing, number slots, credentials, teams, grants or company terms.

The server starts without a token or channel ID so you can install first. Until both are set, every tool returns not_configured with a link to get a free sandbox token at https://hellohop.app, without making an API request. Set both variables and restart the agent. Malformed nonempty settings still fail at startup. Number checks require an eligible account and a non-sandbox channel.

Sending is off by default

Without GATEWAY_ALLOW_SEND=1 no send tool is registered: a client cannot see or call them, and the server never contacts a send endpoint. With it on, every call sends a real WhatsApp message from the linked number (a reaction, its removal and a delete included) and counts as one against the daily message allowance (sandbox channels).

A send can succeed without saying so

A failed send_text carries delivery: "unknown" when the message may have been sent anyway: no response arrived, the API answered ambiguous: true (a 504 send_unconfirmed, with the id of the row it logged), or the answer was any other 502 or 504. Do not send it again. Check read_messages for that chat first. Sending it again is how the same message reaches a real person twice.

Prompt injection: read and send together let strangers steer sends

read_messages puts text written by third parties, anyone who can message the number, into the model's context. With GATEWAY_ALLOW_SEND=1 in the same server, that text can instruct the model to send messages, to anyone, with any content. This is not solved by trusting the client or the person using it: the instructions come from the messages being read.

Run reading and sending as two separate client configurations:

• a read-only entry, without GATEWAY_ALLOW_SEND, for anything that reads messages;
• a send entry, with GATEWAY_ALLOW_SEND=1, enabled only in a session that needs to send, with every send_text call approved by a person who reads its to and text.

The send entry still registers the read tools, so a session using it is exposed the moment it reads messages. Keep that session away from read_messages unless you trust everyone who can message the number.

Claude Desktop

Add an entry to mcpServers in claude_desktop_config.json:

{  "mcpServers": {    "hellohop-mcp": {      "command": "npx",      "args": ["-y", "hellohop-mcp"],      "env": {        "GATEWAY_API_TOKEN": "<CHANNEL_TOKEN>",        "GATEWAY_CHANNEL_ID": "<CHANNEL_ID>"      }    }  }}

Add "GATEWAY_ALLOW_SEND": "1" to env to enable sending. Restart Claude Desktop after editing the file.

Claude Code

claude mcp add hellohop-mcp \  -e GATEWAY_API_TOKEN=<CHANNEL_TOKEN> \  -e GATEWAY_CHANNEL_ID=<CHANNEL_ID> \  -- npx -y hellohop-mcp

Add -e GATEWAY_ALLOW_SEND=1 before -- to enable sending.

Both clients store the token in their configuration file in plain text. Use the channel's own token, never an operator credential.

Cursor

Add the same entry to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

{  "mcpServers": {    "hellohop-mcp": {      "command": "npx",      "args": ["-y", "hellohop-mcp"],      "env": {        "GATEWAY_API_TOKEN": "<CHANNEL_TOKEN>",        "GATEWAY_CHANNEL_ID": "<CHANNEL_ID>"      }    }  }}

Sending stays off unless you add "GATEWAY_ALLOW_SEND": "1" to env.

Example requests

Once connected, ask your assistant in plain language. For example:

• "What is the status of my channel?" (calls channel_status)
• "Show the last 20 messages in my chat with [email protected]." (calls read_messages)
• "List the groups this number is in." (calls list_groups)

License

MIT. Full documentation: https://hellohop.app/docs/mcp