Stealthy browser automation, testing, and web-scraping via CDP Mode.
Nothing to run from here
Buddy phone tools 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.
99/100
trust score
15
downloads a day
local
runs on your machine
722
downloads in 30d
What it does
Needs the free Buddy app on your Android phone, and runs on the phone itself (in Termux, for example).
Download the APK: https://github.com/ghorbelhamdi/buddy-android/releases/latest/download/buddy.apk
Source: https://github.com/ghorbelhamdi/buddy-android
Agents can read the screen, tap, type, scroll and open apps, and use notifications, media, the calendar and a background browser. Buddy asks you before anything risky. No root, no adb, no PC.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'BUDDY_TOKEN=${BUDDY_TOKEN}' --transport stdio buddy-phone-tools-mcp '--' npx -y buddy-phone-bridge
# 2 — ask your agent for something these tools do
# read_screen, tap, long_press and 25 more
It needs BUDDY_TOKEN: this reads it from your environment, so export it first.
Buddy phone tools costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Buddy phone tools as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads BUDDY_TOKEN (Token from Buddy's Settings > Phone tools in your own sessions) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx BUDDY_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'BUDDY_TOKEN=${BUDDY_TOKEN}' --transport stdio buddy-phone-tools-mcp '--' npx -y buddy-phone-bridgeReconnect, 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: BUDDY_TOKEN — Token from Buddy's Settings > Phone tools in your own sessions. You set it 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
28 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 what is on the phone screen as a list of UI elements with ids, text, and tap coordinates. Call this first and after every action to see the result. Element ids are only valid until the next read_screen.
Takes no parameters.
Tap an element (by id from the last read_screen) or a screen coordinate in pixels.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element | integer | no | Element id from read_screen |
| x | integer | no | X in screen pixels |
| y | integer | no | Y in screen pixels |
Press and hold an element (by id from the last read_screen) or a screen coordinate in pixels, for about 0.7 s. Use it for what apps put behind a long press: a message's or item's menu (reply, copy, delete, react), selecting items or text, moving icons. Use tap for normal taps. Returns…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element | integer | no | Element id from read_screen (give this, or x and y) |
| x | integer | no | X in screen pixels, when there's no element id |
| y | integer | no | Y in screen pixels, when there's no element id |
Type into the focused text field (or the given element). Replaces its content unless append is true. Set submit to press the keyboard's enter/send action afterwards.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text to type |
| element | integer | no | Optional element id of the text field |
| append | boolean | no | Append instead of replacing |
| submit | boolean | no | Press the IME enter/send action after typing |
Scroll a list or page by about a third of its height or width, to reach content that isn't on screen yet: 'down' shows what's further down (like reading on), 'up' goes back, 'left'/'right' for carousels and tabs. Without element it scrolls the middle of the screen; give the id of a scrollable…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| direction | string | yes | — |
| element | integer | no | Optional: id of the scrollable element from read_screen |
Drag a finger in a straight line from (x1, y1) to (x2, y2), in screen pixels. Use it for gestures scroll doesn't cover: moving a slider, swiping a card or a message aside, pulling down to refresh, dragging on a map. A very short swipe counts as a tap. Returns "Swiped"; call read_screen to see the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| x1 | integer | yes | Start X in screen pixels |
| y1 | integer | yes | Start Y in screen pixels |
| x2 | integer | yes | End X in screen pixels |
| y2 | integer | yes | End Y in screen pixels |
| duration_ms | integer | no | How long the drag takes, 50 to 3000 ms (default 300); slower is more like dragging, faster like flinging |
Press one of Android's system buttons: back (leave the current screen or close a dialog or the keyboard), home (go to the home screen), recents (the recent apps list), notifications (pull down the notification shade), quick_settings (open Quick Settings). To switch apps, open_app is faster than…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| button | string | yes | — |
Open an installed app by its name (e.g. 'Messenger') or package name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| app | string | yes | App name or package |
List launchable apps with their package names.
Takes no parameters.
Open a link on the phone the way tapping it would: https:// pages open in the user's browser or in the app that handles them (a YouTube link in YouTube), and deep links open their app (mailto: an email draft, tel: the dialer with the number, geo: or a maps link a map, market:// the Play Store).…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The URL or deep link, e.g. https://example.com or tel:+491234 |
Take a screenshot (JPEG). Use only when read_screen is not enough (images, games, canvas UIs). The reply says how to convert image coordinates to screen pixels.
Takes no parameters.
Wait for the UI to settle, up to 10000 ms.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ms | integer | yes | Milliseconds |
Ask the user to approve an action in the Buddy bubble and wait for the answer. REQUIRED before sending messages, posting, buying, deleting, or changing settings. Show the exact text or action. Returns APPROVED, DENIED, or CHANGES REQUESTED with what the user wants changed: then make those changes…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| summary | string | yes | Exactly what you are about to do, including any text to be sent |
Ask the user a question in the Buddy bubble and wait for the answer: 2 to 4 answer buttons, and the user can always type their own answer instead. Use it when you need the user to choose or decide (which reply, which item, which time) instead of guessing. With highlight, it also hands a step over…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | The question, short and clear |
| options | array | yes | 2 to 4 short answers, one per button |
| highlight | array | no | Optional: what the user has to do on the screen before answering (as in point_out), e.g. the fields to fill in. Buddy marks them, and the question waits next to the bubble instead of covering the scre |
| browser_highlight | array | no | Optional, instead of highlight: items in the background browser the user has to use (a sign-in, a captcha, their details). Buddy opens the browser full screen with them marked, and closes it once the |
Show the user where to look or what to do on the screen: a box, circle or arrow with a short label around up to 6 elements, drawn over the app without blocking their touches. When the user does what a mark points at (taps that button, flips that switch, fills in that field and moves on), it turns…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| marks | array | yes | What to point out, e.g. [{"element": 12, "label": "First name"}, {"element": 14, "label": "Last name"}] |
| style | string | no | — |
| wait | boolean | no | Wait until the user has done what the marks point at, or until they can't anymore |
| seconds | integer | no | How long the marks stay at most: default 60 (180 with wait), max 300 |
Show a short status line in the Buddy bubble without stopping.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Status text |
Answer the notification that started this chat through its own reply field, without opening the app. Only in chats started by one of the user's notification rules, when the notification has a reply field. Buddy shows the user an approval card with the text first, unless you called confirm with it…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The reply, exactly as it should be sent |
(Needs Linux tools) Open Android's installer for an APK built in Buddy's Linux, e.g. /root/.buddy/work/myapp/build/app.apk, or served by another app on this phone at a local URL (http://127.0.0.1:<port>/app.apk, e.g. from Termux). The user taps Install/Update themselves; call wait_for_install next.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Full path of the .apk inside Buddy's Linux, or its http://127.0.0.1 URL |
Check whether a newer Buddy is out (the official GitHub release) and what's new; with install=true, download it and open Android's installer. Use it when the user asks to update Buddy or whether there's a new version. Only the user can tap Update.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| install | boolean | no | true: download the update and open the installer (after the user said yes) |
After opening the Android installer for an APK, wait until the user has tapped Install/Update and confirmed. Returns as soon as the package is installed (at least min_version_code if given), or early if the installer is no longer on screen, or after the timeout. Use this instead of shell polling…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| package | string | yes | Package name, e.g. com.buddyapps.flappy |
| min_version_code | integer | no | Wait for at least this versionCode (for updates) |
| timeout_s | integer | no | Default 120, max 300 |
Open a web page in Buddy's background browser (a separate browser the user can watch in this chat; it doesn't use the phone's screen). Returns the page as text, like browser_read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The address, e.g. https://example.com |
| new_tab | boolean | no | Open it in a new tab, keeping the current one |
Read the whole page in the background browser as text. Items you can use are numbered, e.g. [12] button "Add to cart"; the numbers stay valid until the page changes. Long pages come in parts: pass from to read on.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | integer | no | Character to start at, from the previous part's note |
Tap an item on the page by its number from browser_read (a link, button, checkbox, …).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | integer | yes | The item's number |
Type into a text field by its number from browser_read (replaces its text unless append is true), or pick an option of a select by its text. Set submit to press Enter afterwards.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | integer | yes | The field's number |
| text | string | yes | Text to type, or the option to pick |
| append | boolean | no | Add to the field's text instead of replacing it |
| submit | boolean | no | Press Enter afterwards |
Scroll the page in the background browser (loads more on endless pages).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| direction | string | yes | — |
A picture of what the background browser shows, for images, maps or layouts browser_read can't describe.
Takes no parameters.
Go back to the previous page in the current tab of the background browser, like a browser's back button. If the page warns that leaving loses unsaved changes, Buddy stays the first time and says so. Returns where the tab is now, or that there's no previous page; then call browser_read.
Takes no parameters.
Manage the background browser's tabs (this chat's own): with no arguments, list them as numbered lines with title and address, the current one marked; with switch_to, make that tab current (the browser_* tools act on the current tab); with close, close it. Tabs open with browser_open new_tab or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| switch_to | integer | no | Number of the tab to switch to, from the list |
| close | integer | no | Number of the tab to close, from the list |
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 Buddy phone tools 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 99 / 100
Release 1.2.0 · scanned 3 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 score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest95f7c8beb021d23f3b04659cf856dc11806fcece9f7215f0f55e8c7f914333ec
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest95f7c8beb021d23f
Scanned2026-11-03
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 1.2.0. Pin a release below and the command asks for exactly that one.
1.2.0
2 Nov 2026
latestNo release note was published with this version.
1.1.0
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 Buddy phone tools 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.