A personal MCP for WhatsApp, with voice-note and call transcripts.
Nothing to run from here
HelloHop is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
11
downloads a day
local
runs on your machine
753
downloads in 30d
What it does
Read WhatsApp chats and groups, and send messages when allowed, through the HelloHop API.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GATEWAY_API_TOKEN=${GATEWAY_API_TOKEN}' --env 'GATEWAY_CHANNEL_ID=${GATEWAY_CHANNEL_ID}' --transport stdio hellohop-mcp '--' npx -y hellohop-mcp
# 2 — ask your agent for something these tools do
# channel_status, list_chats, read_messages and 12 more
It needs GATEWAY_API_TOKEN, GATEWAY_CHANNEL_ID: this reads them from your environment, so export them first.
HelloHop costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts HelloHop as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GATEWAY_API_TOKEN (The channel's API token), GATEWAY_CHANNEL_ID (The channel ID the token belongs to) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx GATEWAY_API_TOKEN …, setx GATEWAY_CHANNEL_ID … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GATEWAY_API_TOKEN=${GATEWAY_API_TOKEN}' --env 'GATEWAY_CHANNEL_ID=${GATEWAY_CHANNEL_ID}' --transport stdio hellohop-mcp '--' npx -y hellohop-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GATEWAY_API_TOKEN — The channel's API token.; GATEWAY_CHANNEL_ID — The channel ID the token belongs to.. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Read this channel's state from …: whether the number is linked and connected.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_safety | boolean | no | Also read the safety readings (a second GET request). Default false. |
List the chats … has observed on this channel, from its own message log.
No parameter schema on file.
Read one conversation from this channel's message log, newest first: a person or a group.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chat | string | yes | — |
| limit | integer | no | Messages per page, 1 to 500. Default 50. |
| before | string | no | The next_before value of a previous page, exactly as returned. |
List the WhatsApp groups this channel's number is in.
No parameter schema on file.
Read one group: its subject, description, settings and participants.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| group | yes | — |
Read one community this channel's number belongs to.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| community | yes | — |
List the groups linked to a community.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| community | yes | — |
Read this channel's stored entry for one contact (the names its contact store holds); this does not ask WhatsApp.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| who | string | yes | The contact: a user JID or a LID. |
Send a WhatsApp text message from this channel. This sends a real message from a real number
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | yes | A phone number in full international form, country code included, or a WhatsApp JID. |
| text | string | yes | The message text. |
| quoted | string | no | Optional. The ID of a message this channel has in the same chat, to reply to it. |
Send media from this channel. The gateway FETCHES the file from url (http or https, a public address,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | What to send it as. |
| to | string | yes | A phone number in full international form, country code included, or a WhatsApp JID. |
| url | string | yes | Where the gateway fetches the file. |
| caption | string | no | Optional, for image, video and document only. |
| filename | string | no | Optional, for document only: the name the recipient sees. |
| mime_type | string | no | Optional, for document only. |
Send a poll from this channel: a question and 2 to 12 different options, one answer unless multiple is
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | yes | A phone number in full international form, country code included, or a WhatsApp JID. |
| question | string | yes | The question. |
| options | array | yes | The options, each different. |
| multiple | boolean | no | Let a voter choose more than one option. Default false. |
React with one emoji to a message this channel sent or received; a new reaction replaces this
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message_id | string | yes | The id of a message this channel sent or received (the id field from read_messages). |
| emoji | string | yes | One emoji. |
Remove this channel's reaction to a message. WhatsApp sends the removal as a message, so it counts
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message_id | string | yes | The id of a message this channel sent or received (the id field from read_messages). |
Delete for everyone a message this channel's number sent, within 48 hours of sending. Someone else's
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message_id | string | yes | The id of a message this channel sent or received (the id field from read_messages). |
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install HelloHop or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 0.3.2 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 2 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest84563fd1b6b3c2c6a7585c1936cb878f5027ce8a5f286080b5d6fcc0bfffd861
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
6 of the 15 recovered tools are registered only when config.allowSend holds (dist/server.js:274) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 9.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
9 tools are registered unconditionally · 6 more only when config.allowSend holds (dist/server.js:274) — typically when a key or option is configured. All 15 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| channel_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_chats | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| read_messages | untrusted-input | untrusted-input: keyword "read_message", declares openWorldHint: true (interacts with entities outside the server) |
| list_groups | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_group | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_community | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_community_subgroups | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_contact | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| check_numbers | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:251 |
| send_media conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:335 |
| send_poll conditional | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:354 |
| react conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP PUT (request("PUT", …)) at dist/server.js:372 |
| unreact conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP DELETE (request("DELETE", …)) at dist/server.js:385 |
| delete_message conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP DELETE (request("DELETE", …)) at dist/server.js:400 |
| send_text conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:302 |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest84563fd1b6b3c2c6
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.2. Pin a release below and the command asks for exactly that one.
0.3.2
28 Oct 2026
latestNo release note was published with this version.
0.3.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish HelloHop can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.