A TypeScript implementation of a simple MCP server that exposes datetime information to agentic systems and chat REPLs
Nothing to run from here
Hwip 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.
93/100
trust score
15
tools declared
local
runs on your machine
—
downloads a day
What it does
Notify your phone, ask questions and get answers back from AI coding agents via Hwip.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user hwip-mcp '--' npx -y @hwip/mcp-server
# 2 — ask your agent for something these tools do
# hwip_agent_list, hwip_agent_read, hwip_agent_send and 12 more
Hwip costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HWAll 1 server
hwipit1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Hwip 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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user hwip-mcp '--' npx -y @hwip/mcp-serverReconnect, 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
Nothing is required, but it can take HWIP_API_KEY (Your Hwip API key. Optional when ~/.hwip/config.json (from `hwip login`) holds one.) if you want to set 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.
List the agent sessions running on THIS machine (key, agent, state, name).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| all | boolean | no | List every machine of the account (from the server) instead of this one |
Read what another agent session on THIS machine did last: its last turns (the user's prompt, the agent's text, the tools it called with their target — never a tool's output).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | The key from hwip_agent_list (<deviceId>:<tmuxName>), or a name that names exactly one session on this machine |
| turns | integer | no | How many of the latest turns to read (default 3, at most 20) |
Type a message into ANOTHER agent session on any of the user's machines, as if the user sent it from their phone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | Session key <deviceId>:<tmuxName> as given in a [hwip: …] hint or reply: header, or a name matching one session: tmux name, alias, label, or the agent's own session name (Claude Code's, e.g. `ko |
| message | string | yes | Plain text typed into the target session (sealed for it) |
Ask the user a question on their phone: quick-reply buttons plus a text field — they tap or type. Pass actions (2–4 buttons) unless the answer is free-form text. Blocks until they answer or timeout passes. Requires HWIP_HOOK_ID. The question and the answer always go under end-to-end…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Question or request title |
| body | string | no | Context or instructions |
| actions | array | no | Quick-reply buttons (1-4). Expected on nearly every ask — the phone steers by tapping, so put the next-step candidates here (next command, review, stop) plus a Done-like fallback. Omit ONLY when the a |
| placeholder | string | no | Input field placeholder hint |
| inputType | string | no | Input field type (default: text) |
| timeout | number | no | Seconds to wait for response once the question is up (default: 300); a send that fails and is repeated adds its own time before that. Silence returns timedOut: true, with actionId set to `fallback |
| fallback | string | no | Action ID to auto-select on timeout — one of actions, or done/stop/exit to end the loop. Never a danger action: silence must not choose it |
Send a push notification to all subscribers of a channel. Use hwip_channels to find available channels.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| channelId | string | yes | Channel ID to broadcast to (e.g., "ch_...") |
| title | string | yes | Notification title |
| body | string | no | Notification body text |
| url | string | no | Optional URL to open on the device. |
| priority | string | no | Notification priority |
Copy text to the user's device clipboard. The text will appear in their clipboard history and can be pasted immediately. At most 96 KiB (as JSON text); send longer text with hwip_file. Not end-to-end encrypted — do not use it for secrets (keys, tokens, passwords); use hwip_notify or hwip_file for…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text to copy to clipboard |
| targetDeviceId | string | no | Target device ID. Omit to use configured default or send to all devices. |
Dismiss (mark as read) a specific push notification by ID. Use after processing a notification to clear it from the user's feed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pushId | string | yes | Push ID to dismiss (e.g., "push_01HX...") |
Dismiss all push notifications at once. Clears the entire notification feed.
No parameter schema on file.
Send files to the user's device. Pass filePath to send a file that already exists on disk — images (png/jpg/gif/webp/heic), PDFs, logs, anything. Pass filePaths to send several at once (screenshots of one change, a set of logs): they arrive together in one message, five to a push. Pass…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | no | Absolute path to a local file to send. Required for images, PDFs, and any other binary — never base64 a file into content. |
| filePaths | array | no | Absolute paths of several local files to send together, in order (up to …). Use instead of one call per file. Not with filePath or content. |
| content | string | no | Text content of the file. Use only for text you generated; requires fileName. |
| fileName | string | no | File name with extension (e.g., "report.txt"). Required with content; defaults to the basename of filePath. |
| title | string | no | Notification title (defaults to fileName, or the number of files) |
| targetDeviceId | string | no | Target device ID. Omit to use configured default or send to all devices. |
List recent push notifications. Use this to check notification history, avoid duplicates, or reference previous messages. An end-to-end encrypted push shows encrypted: true with no title or body.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Number of pushes to return (default: 5, max: 20) |
| type | string | no | Filter by push type |
List the user's devices with their online status. Use a deviceId as hwip_notify's targetDeviceId to reach one device.
No parameter schema on file.
List the user's channels. Use a channelId with hwip_broadcast to reach a channel's subscribers.
No parameter schema on file.
Send a one-way push notification to the user's devices. Use this to inform the user about task completion, errors, or status updates. Long bodies are automatically uploaded as a file for full viewing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Notification title |
| body | string | no | Notification body text |
| url | string | no | Optional URL to open on the device. |
| priority | string | no | Notification priority. Use "urgent" for critical alerts, "low" for background info. |
| targetDeviceId | string | no | Target device ID. Omit to use configured default or send to all devices. |
Set a custom display name for THIS agent session in the user's Hwip app (the Streams › Agents list).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| alias | string | yes | Display name for this session (max … characters). |
Title THIS session in the user's Hwip app with what it is working on, so the user can tell sessions apart.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | What this session is doing (max … characters). |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Hwip 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 93 / 100
Release 0.1.7 · scanned 6 Nov 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 score93
Findings2 threat · 3 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestf5a0c82e087afde2244f2ac4374635ffd25374e3374435629d54f0b670258473
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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>".
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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| hwip_agent_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hwip_agent_read | no tags | |
| hwip_agent_send | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hwip_ask | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_broadcast | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_clipboard | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_dismiss | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_dismiss_all | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| hwip_file | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hwip_devices | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hwip_channels | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hwip_notify | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_session_rename | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| hwip_session_title | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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 digestf5a0c82e087afde2
Scanned2026-11-06
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 0.1.7. Pin a release below and the command asks for exactly that one.
0.1.7
undated
latestNo release note was published with this version.
—
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 Hwip 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.